diff --git a/quick_test/96_matrix_add_bad.ll b/quick_test/96_matrix_add_bad.ll
new file mode 100644
index 0000000..05cfe19
--- /dev/null
+++ b/quick_test/96_matrix_add_bad.ll
@@ -0,0 +1,111 @@
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+@N = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @add(float* %a0, float* %a1, float* %a2, float* %b0, float* %b1, float* %b2, float* %c0, float* %c1, float* %c2) {
+entry:
+br label %cond0
+
+cond0:
+%phi_141 = phi i32 [0, %entry], [%Add_69, %body1]
+%load_73 = load i32, ptr @M
+%icmp_74 = icmp slt i32 %phi_141, %load_73
+br i1 %icmp_74, label %body1, label %exit
+
+body1:
+%getelementptr_31 = getelementptr float, ptr %a0, i32 %phi_141
+%getelementptr_34 = getelementptr float, ptr %b0, i32 %phi_141
+%load_35 = load float, ptr %getelementptr_31
+%load_36 = load float, ptr %getelementptr_34
+%FAdd_37 = fadd float %load_35, %load_36
+%getelementptr_40 = getelementptr float, ptr %c0, i32 %phi_141
+store float %FAdd_37, ptr %getelementptr_40
+%getelementptr_44 = getelementptr float, ptr %a1, i32 %phi_141
+%getelementptr_47 = getelementptr float, ptr %b1, i32 %phi_141
+%load_48 = load float, ptr %getelementptr_44
+%load_49 = load float, ptr %getelementptr_47
+%FAdd_50 = fadd float %load_48, %load_49
+%getelementptr_53 = getelementptr float, ptr %c1, i32 %phi_141
+store float %FAdd_50, ptr %getelementptr_53
+%getelementptr_57 = getelementptr float, ptr %a2, i32 %phi_141
+%getelementptr_60 = getelementptr float, ptr %b2, i32 %phi_141
+%load_61 = load float, ptr %getelementptr_57
+%load_62 = load float, ptr %getelementptr_60
+%FAdd_63 = fadd float %load_61, %load_62
+%getelementptr_66 = getelementptr float, ptr %c2, i32 %phi_141
+store float %FAdd_63, ptr %getelementptr_66
+%Add_69 = add i32 %phi_141, 1
+br label %cond0
+
+exit:
+ret i32 0
+
+
+}
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_86 = alloca [3 x float]
+%alloca_87 = alloca [3 x float]
+%alloca_88 = alloca [3 x float]
+%alloca_89 = alloca [3 x float]
+%alloca_90 = alloca [3 x float]
+%alloca_91 = alloca [3 x float]
+%getelementptr_143 = getelementptr [3 x float], ptr %alloca_88, i32 0
+%getelementptr_144 = getelementptr [3 x float], ptr %alloca_91, i32 0
+%getelementptr_145 = getelementptr [3 x float], ptr %alloca_89, i32 0
+%getelementptr_146 = getelementptr [3 x float], ptr %alloca_86, i32 0
+%getelementptr_147 = getelementptr [3 x float], ptr %alloca_90, i32 0
+%getelementptr_148 = getelementptr [3 x float], ptr %alloca_87, i32 0
+%call_149 = call i32 @thrd_create(i32 4)
+%Mul_151 = mul i32 %call_149, 3
+%SDiv_152 = sdiv i32 %Mul_151, 5
+%Add_154 = add i32 %Mul_151, 3
+%SDiv_155 = sdiv i32 %Add_154, 5
+br label %cond0
+
+cond0:
+%phi_142 = phi i32 [%SDiv_152, %entry], [%Add_132, %body1]
+%icmp_157 = icmp slt i32 %phi_142, %SDiv_155
+br i1 %icmp_157, label %body1, label %exit
+
+body1:
+%getelementptr_102 = getelementptr [3 x float], ptr %getelementptr_146, i32 0, i32 %phi_142
+%itofp_104 = sitofp i32 %phi_142 to float
+store float %itofp_104, ptr %getelementptr_102
+%getelementptr_107 = getelementptr [3 x float], ptr %getelementptr_148, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_107
+%getelementptr_112 = getelementptr [3 x float], ptr %getelementptr_143, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_112
+%getelementptr_117 = getelementptr [3 x float], ptr %getelementptr_145, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_117
+%getelementptr_122 = getelementptr [3 x float], ptr %getelementptr_147, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_122
+%getelementptr_127 = getelementptr [3 x float], ptr %getelementptr_144, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_127
+%Add_132 = add i32 %phi_142, 1
+br label %cond0
+
+exit:
+call void @thrd_join()
+ret i32 0
+
+
+}
diff --git a/quick_test/96_matrix_add_bad.s b/quick_test/96_matrix_add_bad.s
new file mode 100644
index 0000000..581d51e
--- /dev/null
+++ b/quick_test/96_matrix_add_bad.s
@@ -0,0 +1,211 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.text
+.align	3
+.globl	add
+.type	add, @function
+add:
+.Ladd_entry:
+mv t1,a5
+sd s0,-8(sp)
+mv t2,a6
+mv t0,a4
+mv s0,sp
+sd s3,-48(s0)
+addi sp,sp,-48
+sd s2,-40(s0)
+mv s3,a1
+li a1,0
+sd s4,-32(s0)
+mv s2,a0
+mv s4,a2
+sd s1,-24(s0)
+mv a2,a3
+ld a0,0(s0)
+mv s1,a7
+j .Ladd_cond0
+.Ladd_cond0:
+lla a4,M
+lw a3,0(a4)
+slt a4,a1,a3
+bge a1,a3,.Ladd_exit
+j .Ladd_body1
+.Ladd_body1:
+slli a3,a1,2
+add a4,s2,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,a2,a3
+flw ft1,0(a5)
+slli a3,a1,2
+add a4,t2,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s3,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t0,a3
+slli a3,a1,2
+flw ft1,0(a5)
+add a4,s1,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s4,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t1,a3
+flw ft1,0(a5)
+slli a3,a1,2
+add a4,a0,a3
+addiw a3,a1,1
+fadd.s ft2,ft0,ft1
+mv a1,a3
+fsw ft2,0(a4)
+j .Ladd_cond0
+.Ladd_exit:
+ld s1,-24(s0)
+mv sp,s0
+ld s2,-40(s0)
+addiw a0,zero,0
+ld s3,-48(s0)
+ld s4,-32(s0)
+ld s0,-8(s0)
+ret
+.size	add, .-add
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+sd s0,-16(sp)
+lla t1,N
+li t0,3
+sw t0,0(t1)
+mv s0,sp
+addi a1,s0,-96
+addi t2,s0,-144
+li t0,3
+addi sp,sp,-144
+sd ra,-8(s0)
+lla t1,M
+sw t0,0(t1)
+addi a0,s0,-108
+sd s1,112(sp)
+li t0,3
+lla t1,L
+sw t0,0(t1)
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-84
+add s1,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-120
+add a2,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+slli t2,t1,2
+add t1,a0,t2
+sd t1,104(sp)
+addi t2,zero,0
+slli a0,t2,2
+add t2,a1,a0
+sd t2,96(sp)
+addi a0,zero,0
+slli a3,a0,2
+addi a0,s0,-132
+add a1,a0,a3
+li a0,4
+sd a1,88(sp)
+sd a2,80(sp)
+sd t0,-72(s0)
+call thrd_create
+ld t1,104(sp)
+mv a4,a0
+slliw a3,a4,0
+slliw a0,a4,2
+subw a4,a0,a3
+ld t2,96(sp)
+li a0,5
+ld a2,80(sp)
+div a5,a4,a0
+ld a1,88(sp)
+ld t0,-72(s0)
+addiw a6,a4,3
+li a3,5
+div a0,a6,a3
+mv a3,a5
+j .Lmain_cond0
+.Lmain_cond0:
+slt a4,a3,a0
+bge a3,a0,.Lmain_exit
+j .Lmain_body1
+.Lmain_body1:
+addi a4,a3,0
+fcvt.s.w ft0,a3
+slli a5,a4,2
+add a4,t0,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,t2,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,a2,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,a1,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,s1,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,t1,a5
+fsw ft0,0(a4)
+addiw a4,a3,1
+mv a3,a4
+j .Lmain_cond0
+.Lmain_exit:
+call thrd_join
+ld ra,-8(s0)
+addiw a0,zero,0
+ld s1,112(sp)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/96_matrix_add_good.ll b/quick_test/96_matrix_add_good.ll
new file mode 100644
index 0000000..2bca9c5
--- /dev/null
+++ b/quick_test/96_matrix_add_good.ll
@@ -0,0 +1,95 @@
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+@N = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @add(float* %a0, float* %a1, float* %a2, float* %b0, float* %b1, float* %b2, float* %c0, float* %c1, float* %c2) {
+entry:
+br label %cond0
+
+cond0:
+%phi_121 = phi i32 [0, %entry], [%Add_69, %body1]
+%load_73 = load i32, ptr @M
+%icmp_74 = icmp slt i32 %phi_121, %load_73
+br i1 %icmp_74, label %body1, label %exit
+
+body1:
+%getelementptr_31 = getelementptr float, ptr %a0, i32 %phi_121
+%getelementptr_34 = getelementptr float, ptr %b0, i32 %phi_121
+%load_35 = load float, ptr %getelementptr_31
+%load_36 = load float, ptr %getelementptr_34
+%FAdd_37 = fadd float %load_35, %load_36
+%getelementptr_40 = getelementptr float, ptr %c0, i32 %phi_121
+store float %FAdd_37, ptr %getelementptr_40
+%getelementptr_44 = getelementptr float, ptr %a1, i32 %phi_121
+%getelementptr_47 = getelementptr float, ptr %b1, i32 %phi_121
+%load_48 = load float, ptr %getelementptr_44
+%load_49 = load float, ptr %getelementptr_47
+%FAdd_50 = fadd float %load_48, %load_49
+%getelementptr_53 = getelementptr float, ptr %c1, i32 %phi_121
+store float %FAdd_50, ptr %getelementptr_53
+%getelementptr_57 = getelementptr float, ptr %a2, i32 %phi_121
+%getelementptr_60 = getelementptr float, ptr %b2, i32 %phi_121
+%load_61 = load float, ptr %getelementptr_57
+%load_62 = load float, ptr %getelementptr_60
+%FAdd_63 = fadd float %load_61, %load_62
+%getelementptr_66 = getelementptr float, ptr %c2, i32 %phi_121
+store float %FAdd_63, ptr %getelementptr_66
+%Add_69 = add i32 %phi_121, 1
+br label %cond0
+
+exit:
+ret i32 0
+
+
+}
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_86 = alloca [3 x float]
+%alloca_87 = alloca [3 x float]
+%getelementptr_123 = getelementptr [3 x float], ptr %alloca_87, i32 0
+%getelementptr_124 = getelementptr [3 x float], ptr %alloca_86, i32 0
+%call_125 = call i32 @thrd_create(i32 4)
+%Mul_127 = mul i32 %call_125, 3
+%SDiv_128 = sdiv i32 %Mul_127, 5
+%Add_130 = add i32 %Mul_127, 3
+%SDiv_131 = sdiv i32 %Add_130, 5
+br label %cond0
+
+cond0:
+%phi_122 = phi i32 [%SDiv_128, %entry], [%Add_112, %body1]
+%icmp_133 = icmp slt i32 %phi_122, %SDiv_131
+br i1 %icmp_133, label %body1, label %exit
+
+body1:
+%getelementptr_102 = getelementptr [3 x float], ptr %getelementptr_124, i32 0, i32 %phi_122
+%itofp_104 = sitofp i32 %phi_122 to float
+store float %itofp_104, ptr %getelementptr_102
+%getelementptr_107 = getelementptr [3 x float], ptr %getelementptr_123, i32 0, i32 %phi_122
+store float %itofp_104, ptr %getelementptr_107
+%Add_112 = add i32 %phi_122, 1
+br label %cond0
+
+exit:
+call void @thrd_join()
+ret i32 0
+
+
+}
diff --git a/quick_test/96_matrix_add_good.s b/quick_test/96_matrix_add_good.s
new file mode 100644
index 0000000..f3ee484
--- /dev/null
+++ b/quick_test/96_matrix_add_good.s
@@ -0,0 +1,173 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.text
+.align	3
+.globl	add
+.type	add, @function
+add:
+.Ladd_entry:
+mv t0,a4
+mv t2,a6
+sd s0,-8(sp)
+mv t1,a5
+mv s0,sp
+addi sp,sp,-48
+sd s4,-48(s0)
+mv s4,a2
+sd s2,-40(s0)
+mv a2,a3
+sd s3,-32(s0)
+mv s2,a0
+sd s1,-24(s0)
+mv s3,a1
+li a1,0
+mv s1,a7
+ld a0,0(s0)
+j .Ladd_cond0
+.Ladd_cond0:
+lla a4,M
+lw a3,0(a4)
+slt a4,a1,a3
+bge a1,a3,.Ladd_exit
+j .Ladd_body1
+.Ladd_body1:
+slli a3,a1,2
+add a4,s2,a3
+flw ft0,0(a4)
+slli a3,a1,2
+add a5,a2,a3
+flw ft1,0(a5)
+slli a3,a1,2
+add a4,t2,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s3,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t0,a3
+slli a3,a1,2
+flw ft1,0(a5)
+add a4,s1,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s4,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t1,a3
+slli a3,a1,2
+flw ft1,0(a5)
+add a4,a0,a3
+addiw a3,a1,1
+fadd.s ft2,ft0,ft1
+mv a1,a3
+fsw ft2,0(a4)
+j .Ladd_cond0
+.Ladd_exit:
+ld s2,-40(s0)
+mv sp,s0
+addiw a0,zero,0
+ld s1,-24(s0)
+ld s4,-48(s0)
+ld s3,-32(s0)
+ld s0,-8(s0)
+ret
+.size	add, .-add
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+lla t1,N
+sd s0,-16(sp)
+li a0,4
+li t0,3
+sw t0,0(t1)
+mv s0,sp
+sd ra,-8(s0)
+addi sp,sp,-64
+lla t1,M
+li t0,3
+sw t0,0(t1)
+addi t2,s0,-64
+sd s1,40(sp)
+li t0,3
+lla t1,L
+sw t0,0(t1)
+addi t0,zero,0
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+sd t0,-32(s0)
+slli t2,t1,2
+addi t1,s0,-52
+add a1,t1,t2
+sd a1,-40(s0)
+call thrd_create
+ld t0,-32(s0)
+mv t1,a0
+slliw t2,t1,2
+slliw s1,t1,0
+subw t1,t2,s1
+ld a1,-40(s0)
+li s1,5
+div t2,t1,s1
+addiw s1,t1,3
+li t1,5
+div a0,s1,t1
+mv s1,t2
+j .Lmain_cond0
+.Lmain_cond0:
+slt t1,s1,a0
+bge s1,a0,.Lmain_exit
+j .Lmain_body1
+.Lmain_body1:
+addi t1,s1,0
+fcvt.s.w ft0,s1
+slli t2,t1,2
+add t1,a1,t2
+fsw ft0,0(t1)
+addi t1,s1,0
+slli t2,t1,2
+add t1,t0,t2
+fsw ft0,0(t1)
+addiw t1,s1,1
+mv s1,t1
+j .Lmain_cond0
+.Lmain_exit:
+call thrd_join
+addiw a0,zero,0
+ld s1,40(sp)
+ld ra,-8(s0)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/3.s b/quick_test/asm/3.s
new file mode 100644
index 0000000..d709a62
--- /dev/null
+++ b/quick_test/asm/3.s
@@ -0,0 +1,79 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.bss
+.align	3
+.globl	A
+.type	A, @object
+.size	A, 36
+A:
+.zero	36
+.bss
+.align	3
+.globl	B
+.type	B, @object
+.size	B, 36
+B:
+.zero	36
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+sd s0,-16(sp)
+lla t0,A
+addi t1,t0,0
+mv a0,t1
+mv s0,sp
+addi sp,sp,-32
+sd ra,-8(s0)
+sd s1,-32(s0)
+call getarray
+li a0,4
+call thrd_create
+mv t0,a0
+slliw t1,t0,3
+li t0,5
+div t2,t1,t0
+addiw t0,t1,8
+li t1,5
+div s1,t0,t1
+mv t0,t2
+j .Lmain_cond0
+.Lmain_cond0:
+slt t1,t0,s1
+bge t0,s1,.Lmain_exit
+j .Lmain_body1
+.Lmain_body1:
+addiw a0,t0,1
+addi t1,a0,0
+slli t0,t1,2
+lla t1,A
+add t2,t1,t0
+addi t0,a0,0
+slli a1,t0,2
+lla t0,B
+add t1,t0,a1
+lw t0,0(t2)
+sw t0,0(t1)
+mv t0,a0
+j .Lmain_cond0
+.Lmain_exit:
+call thrd_join
+lla t0,B
+li a0,8
+addi t1,t0,0
+mv a1,t1
+call putarray
+addiw a0,zero,0
+ld s1,-32(s0)
+ld ra,-8(s0)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/6.s b/quick_test/asm/6.s
new file mode 100644
index 0000000..8a1df83
--- /dev/null
+++ b/quick_test/asm/6.s
@@ -0,0 +1,60 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	3
+.globl	A
+.type	A, @object
+.size	A, 36
+A:
+.word	0x1
+.word	0x1
+.word	0x4
+.word	0x5
+.word	0x1
+.word	0x4
+.zero	12
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_exit:
+sd s0,-16(sp)
+lla t0,A
+addi t2,t0,0
+li a0,4
+li t0,11
+mv s0,sp
+addi sp,sp,-32
+sd ra,-8(s0)
+sd s1,-24(s0)
+sw t0,0(t2)
+sd t2,-32(s0)
+call thrd_create
+ld t2,-32(s0)
+mv t1,a0
+addi t0,t1,0
+slli t1,t0,2
+lla t0,A
+add s1,t0,t1
+lw t0,0(s1)
+slliw t1,t0,1
+sw t1,0(s1)
+sd t2,-32(s0)
+call thrd_join
+ld t2,-32(s0)
+li a0,8
+mv a1,t2
+call putarray
+addiw a0,zero,0
+ld s1,-24(s0)
+mv sp,s0
+ld ra,-8(s0)
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/7.s b/quick_test/asm/7.s
new file mode 100644
index 0000000..3ddf963
--- /dev/null
+++ b/quick_test/asm/7.s
@@ -0,0 +1,68 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	3
+.globl	A
+.type	A, @object
+.size	A, 36
+A:
+.word	0x1
+.word	0x1
+.word	0x4
+.word	0x5
+.word	0x1
+.word	0x4
+.zero	12
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_exit:
+li a0,4
+sd s0,-16(sp)
+mv s0,sp
+sd ra,-8(s0)
+addi sp,sp,-32
+sd s1,-32(s0)
+call thrd_create
+mv t0,a0
+addi t1,t0,0
+slli t0,t1,2
+lla t1,A
+add t2,t1,t0
+lw t0,0(t2)
+slliw t1,t0,1
+sw t1,0(t2)
+call thrd_join
+li a0,8
+lla t0,A
+addi s1,t0,0
+mv a1,s1
+call putarray
+li a0,4
+call thrd_create
+mv t1,a0
+addi t0,t1,0
+slli t1,t0,2
+lla t0,A
+add t2,t0,t1
+lw t0,0(t2)
+slliw t1,t0,1
+sw t1,0(t2)
+call thrd_join
+mv a1,s1
+li a0,8
+call putarray
+addiw a0,zero,0
+mv sp,s0
+ld s1,-32(s0)
+ld ra,-8(s0)
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/96_matrix_add.s b/quick_test/asm/96_matrix_add.s
new file mode 100644
index 0000000..847aba9
--- /dev/null
+++ b/quick_test/asm/96_matrix_add.s
@@ -0,0 +1,211 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.text
+.align	3
+.globl	add
+.type	add, @function
+add:
+.Ladd_entry:
+sd s0,-8(sp)
+mv t1,a5
+mv t2,a6
+mv t0,a4
+mv s0,sp
+sd s2,-48(s0)
+addi sp,sp,-48
+sd s3,-40(s0)
+mv s2,a0
+mv s3,a1
+sd s4,-32(s0)
+li a1,0
+mv s4,a2
+sd s1,-24(s0)
+mv a2,a3
+ld a0,0(s0)
+mv s1,a7
+j .Ladd_cond0
+.Ladd_cond0:
+lla a4,M
+lw a3,0(a4)
+slt a4,a1,a3
+bge a1,a3,.Ladd_exit
+j .Ladd_body1
+.Ladd_body1:
+slli a3,a1,2
+add a4,s2,a3
+flw ft0,0(a4)
+slli a3,a1,2
+add a5,a2,a3
+slli a3,a1,2
+flw ft1,0(a5)
+add a4,t2,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s3,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t0,a3
+slli a3,a1,2
+flw ft1,0(a5)
+add a4,s1,a3
+slli a3,a1,2
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+add a4,s4,a3
+slli a3,a1,2
+flw ft0,0(a4)
+add a5,t1,a3
+flw ft1,0(a5)
+slli a3,a1,2
+add a4,a0,a3
+addiw a3,a1,1
+mv a1,a3
+fadd.s ft2,ft0,ft1
+fsw ft2,0(a4)
+j .Ladd_cond0
+.Ladd_exit:
+addiw a0,zero,0
+ld s3,-40(s0)
+mv sp,s0
+ld s2,-48(s0)
+ld s4,-32(s0)
+ld s1,-24(s0)
+ld s0,-8(s0)
+ret
+.size	add, .-add
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+li t0,3
+lla t1,N
+sd s0,-16(sp)
+sw t0,0(t1)
+mv s0,sp
+addi a1,s0,-144
+addi sp,sp,-144
+sd ra,-8(s0)
+addi t2,s0,-108
+addi a0,s0,-132
+li t0,3
+lla t1,M
+sw t0,0(t1)
+sd s1,112(sp)
+li t0,3
+lla t1,L
+sw t0,0(t1)
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-84
+add s1,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-96
+add a2,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+slli t2,t1,2
+add t1,a0,t2
+sd t1,104(sp)
+addi t2,zero,0
+slli a0,t2,2
+add t2,a1,a0
+sd t2,96(sp)
+addi a0,zero,0
+slli a3,a0,2
+addi a0,s0,-120
+add a1,a0,a3
+li a0,4
+sd a1,88(sp)
+sd a2,80(sp)
+sd t0,-72(s0)
+call thrd_create
+ld t1,104(sp)
+mv a4,a0
+slliw a0,a4,2
+ld a2,80(sp)
+ld t0,-72(s0)
+slliw a3,a4,0
+subw a4,a0,a3
+ld a1,88(sp)
+li a0,5
+li a3,5
+div a5,a4,a0
+addiw a6,a4,3
+ld t2,96(sp)
+div a0,a6,a3
+mv a3,a5
+j .Lmain_cond0
+.Lmain_cond0:
+slt a4,a3,a0
+bge a3,a0,.Lmain_exit
+j .Lmain_body1
+.Lmain_body1:
+addi a4,a3,0
+fcvt.s.w ft0,a3
+slli a5,a4,2
+add a4,t1,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,a1,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,s1,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,t0,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,t2,a5
+fsw ft0,0(a4)
+addi a4,a3,0
+slli a5,a4,2
+add a4,a2,a5
+fsw ft0,0(a4)
+addiw a4,a3,1
+mv a3,a4
+j .Lmain_cond0
+.Lmain_exit:
+call thrd_join
+addiw a0,zero,0
+ld s1,112(sp)
+ld ra,-8(s0)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/97_matrix_sub.s b/quick_test/asm/97_matrix_sub.s
new file mode 100644
index 0000000..7cae8d1
--- /dev/null
+++ b/quick_test/asm/97_matrix_sub.s
@@ -0,0 +1,381 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+sd s0,-16(sp)
+li t0,3
+lla t1,N
+sw t0,0(t1)
+mv s0,sp
+addi a0,s0,-128
+addi a2,s0,-224
+li t0,3
+addi t2,s0,-116
+addi sp,sp,-224
+lla t1,M
+sw t0,0(t1)
+sd ra,-8(s0)
+lla t1,L
+li t0,3
+sd s3,184(sp)
+sw t0,0(t1)
+sd s1,192(sp)
+addi t0,zero,0
+slli t1,t0,2
+sd s2,200(sp)
+addi s1,s0,-212
+addi t0,s0,-200
+add a1,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-140
+add a3,t0,t1
+addi t0,zero,0
+sd a3,152(sp)
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+slli t2,t1,2
+add t1,s1,t2
+addi t2,zero,0
+sd t1,144(sp)
+slli s1,t2,2
+add t2,a0,s1
+addi s1,zero,0
+sd t2,136(sp)
+slli a0,s1,2
+add s1,a2,a0
+li a0,4
+sd a1,128(sp)
+sd t0,120(sp)
+call thrd_create
+mv a2,a0
+ld a3,152(sp)
+ld t0,120(sp)
+slliw a4,a2,2
+ld t1,144(sp)
+slliw a0,a2,0
+ld t2,136(sp)
+subw a2,a4,a0
+addiw a4,a2,3
+li a0,5
+div a5,a2,a0
+ld a1,128(sp)
+li a0,5
+div a2,a4,a0
+mv a0,a5
+j .Lmain_cond0
+.Lmain_cond0:
+slt a4,a0,a2
+bge a0,a2,.Lmain_entry_inline0
+j .Lmain_body1
+.Lmain_body1:
+fcvt.s.w ft0,a0
+addi a5,a0,0
+slli a4,a5,2
+add a5,t0,a4
+addi a4,a0,0
+fsw ft0,0(a5)
+slli a5,a4,2
+add a4,s1,a5
+addi a5,a0,0
+fsw ft0,0(a4)
+slli a4,a5,2
+add a5,t1,a4
+fsw ft0,0(a5)
+addi a4,a0,0
+slli a5,a4,2
+add a4,a3,a5
+addi a5,a0,0
+fsw ft0,0(a4)
+slli a4,a5,2
+add a5,t2,a4
+addi a4,a0,0
+fsw ft0,0(a5)
+slli a5,a4,2
+add a4,a1,a5
+fsw ft0,0(a4)
+addiw a4,a0,1
+mv a0,a4
+j .Lmain_cond0
+.Lmain_entry_inline0:
+call thrd_join
+addi s1,s0,-200
+addi t1,zero,0
+slli t0,t1,2
+addi t2,s0,-224
+add t1,t2,t0
+addi a0,s0,-140
+addi t2,zero,0
+slli t0,t2,2
+add t2,s1,t0
+addi s1,zero,0
+slli t0,s1,2
+add s1,a0,t0
+addi a0,zero,0
+slli t0,a0,2
+addi a0,s0,-152
+add a1,a0,t0
+addi t0,zero,0
+slli a0,t0,2
+addi t0,s0,-188
+add a2,t0,a0
+addi t0,zero,0
+slli a0,t0,2
+addi t0,s0,-128
+add a3,t0,a0
+addi t0,zero,0
+sd a3,176(sp)
+slli a0,t0,2
+addi t0,s0,-116
+add a4,t0,a0
+sd t1,168(sp)
+addi t0,zero,0
+slli a0,t0,2
+addi t0,s0,-212
+sd a4,160(sp)
+add a5,t0,a0
+addi t0,zero,0
+slli a0,t0,2
+sd t2,152(sp)
+addi t0,s0,-176
+add a6,t0,a0
+li a0,4
+sd a1,144(sp)
+sd a5,136(sp)
+sd a2,128(sp)
+sd a6,120(sp)
+call thrd_create
+ld t1,168(sp)
+mv a7,a0
+ld a3,176(sp)
+slliw t0,a7,0
+ld t2,152(sp)
+slliw a0,a7,2
+ld a5,136(sp)
+subw s2,a0,t0
+ld a4,160(sp)
+addiw s3,s2,3
+ld a2,128(sp)
+li t0,5
+div a7,s2,t0
+ld a1,144(sp)
+ld a6,120(sp)
+li t0,5
+div a0,s3,t0
+mv t0,a7
+j .Lmain_cond0_inline1
+.Lmain_cond0_inline1:
+slt a7,t0,a0
+bge t0,a0,.Lmain_final2_split5
+j .Lmain_body1_inline4
+.Lmain_body1_inline4:
+addi s3,t0,0
+addi a7,t0,0
+slli s2,a7,2
+add a7,a4,s2
+flw ft0,0(a7)
+slli s2,s3,2
+add s3,s1,s2
+flw ft2,0(s3)
+addi a7,t0,0
+slli s2,a7,2
+add a7,a6,s2
+fsub.s ft1,ft0,ft2
+addi s2,t0,0
+fsw ft1,0(a7)
+slli a7,s2,2
+add s2,t1,a7
+flw ft1,0(s2)
+addi a7,t0,0
+slli s3,a7,2
+add a7,a3,s3
+flw ft0,0(a7)
+fsub.s ft2,ft1,ft0
+addi a7,t0,0
+slli s2,a7,2
+add a7,a2,s2
+addi s2,t0,0
+fsw ft2,0(a7)
+slli a7,s2,2
+add s2,a5,a7
+flw ft0,0(s2)
+addi a7,t0,0
+slli s3,a7,2
+add a7,t2,s3
+flw ft2,0(a7)
+addi s2,t0,0
+fsub.s ft1,ft0,ft2
+slli a7,s2,2
+add s2,a1,a7
+addiw a7,t0,1
+mv t0,a7
+fsw ft1,0(s2)
+j .Lmain_cond0_inline1
+.Lmain_final2_split5:
+call thrd_join
+addi t1,zero,0
+li a0,4
+slli t0,t1,2
+addi t1,s0,-176
+add t2,t1,t0
+sd t2,120(sp)
+call thrd_create
+ld t2,120(sp)
+mv t1,a0
+slliw t0,t1,0
+slliw s1,t1,2
+subw t1,s1,t0
+li t0,5
+addiw s1,t1,3
+div a0,t1,t0
+li t1,5
+div t0,s1,t1
+mv s1,a0
+j .Lmain_cond3
+.Lmain_cond3:
+slt t1,s1,t0
+bge s1,t0,.Lmain_final5
+j .Lmain_body4
+.Lmain_body4:
+addi a0,s1,0
+slli t1,a0,2
+add a0,t2,t1
+flw ft0,0(a0)
+sd t0,128(sp)
+fcvt.w.s t1,ft0,rtz
+sd t2,120(sp)
+mv a0,t1
+call putint
+ld t2,120(sp)
+addiw t1,s1,1
+ld t0,128(sp)
+mv s1,t1
+j .Lmain_cond3
+.Lmain_final5:
+call thrd_join
+li a0,10
+call putch
+li a0,4
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-188
+add s1,t0,t1
+call thrd_create
+mv t1,a0
+slliw t0,t1,2
+slliw t2,t1,0
+subw a0,t0,t2
+li t0,5
+addiw a1,a0,3
+div t1,a0,t0
+li t2,5
+div t0,a1,t2
+mv t2,t1
+j .Lmain_cond6
+.Lmain_cond6:
+slt t1,t2,t0
+bge t2,t0,.Lmain_final8
+j .Lmain_body7
+.Lmain_body7:
+addi a0,t2,0
+slli t1,a0,2
+add a0,s1,t1
+flw ft0,0(a0)
+fcvt.w.s t1,ft0,rtz
+sd t0,128(sp)
+sd t2,120(sp)
+mv a0,t1
+call putint
+ld t0,128(sp)
+ld t2,120(sp)
+addiw t1,t2,1
+mv t2,t1
+j .Lmain_cond6
+.Lmain_final8:
+call thrd_join
+li a0,10
+call putch
+addi t1,zero,0
+li a0,4
+slli t0,t1,2
+addi t2,s0,-152
+add t1,t2,t0
+sd t1,120(sp)
+call thrd_create
+ld t1,120(sp)
+mv t2,a0
+slliw s1,t2,0
+slliw t0,t2,2
+subw t2,t0,s1
+li t0,5
+div s1,t2,t0
+addiw t0,t2,3
+li t2,5
+div a1,t0,t2
+mv t0,s1
+j .Lmain_cond9
+.Lmain_cond9:
+slt t2,t0,a1
+bge t0,a1,.Lmain_exit
+j .Lmain_body10
+.Lmain_body10:
+addi t2,t0,0
+slli s1,t2,2
+add t2,t1,s1
+flw ft0,0(t2)
+fcvt.w.s t2,ft0,rtz
+sd t1,136(sp)
+sd t0,128(sp)
+mv a0,t2
+sd a1,120(sp)
+call putint
+ld a1,120(sp)
+ld t1,136(sp)
+ld t0,128(sp)
+addiw t2,t0,1
+mv t0,t2
+j .Lmain_cond9
+.Lmain_exit:
+call thrd_join
+li a0,10
+call putch
+ld s1,192(sp)
+addiw a0,zero,0
+ld s3,184(sp)
+ld s2,200(sp)
+ld ra,-8(s0)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/98_matrix_mul.s b/quick_test/asm/98_matrix_mul.s
new file mode 100644
index 0000000..0bd967f
--- /dev/null
+++ b/quick_test/asm/98_matrix_mul.s
@@ -0,0 +1,366 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+lla t1,N
+sd s0,-16(sp)
+li t0,3
+sw t0,0(t1)
+mv s0,sp
+sd ra,-8(s0)
+addi a2,s0,-196
+addi sp,sp,-208
+lla t1,M
+addi a0,sp,108
+li t0,3
+fsd fs0,160(sp)
+addi t2,s0,-172
+sw t0,0(t1)
+sd s1,168(sp)
+li t0,3
+lla t1,L
+sw t0,0(t1)
+addi s1,s0,-208
+fsd fs1,176(sp)
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-136
+add a1,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-184
+add a3,t0,t1
+addi t0,zero,0
+sd a3,152(sp)
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+slli t2,t1,2
+add t1,s1,t2
+addi t2,zero,0
+sd t1,144(sp)
+slli s1,t2,2
+add t2,a0,s1
+addi s1,zero,0
+sd t2,136(sp)
+slli a0,s1,2
+add s1,a2,a0
+li a0,4
+sd a1,128(sp)
+sd t0,120(sp)
+call thrd_create
+ld a1,128(sp)
+mv a2,a0
+ld t2,136(sp)
+slliw a0,a2,2
+ld a3,152(sp)
+slliw a4,a2,0
+ld t1,144(sp)
+subw a2,a0,a4
+li a0,5
+ld t0,120(sp)
+div a5,a2,a0
+li a4,5
+addiw a0,a2,3
+div a2,a0,a4
+mv a0,a5
+j .Lmain_cond0
+.Lmain_cond0:
+slt a4,a0,a2
+bge a0,a2,.Lmain_final2_split2
+j .Lmain_body1
+.Lmain_body1:
+fcvt.s.w ft0,a0
+addi a5,a0,0
+slli a4,a5,2
+add a5,a1,a4
+addi a4,a0,0
+fsw ft0,0(a5)
+slli a5,a4,2
+add a4,s1,a5
+fsw ft0,0(a4)
+addi a5,a0,0
+slli a4,a5,2
+add a5,a3,a4
+addi a4,a0,0
+fsw ft0,0(a5)
+slli a5,a4,2
+add a4,t2,a5
+fsw ft0,0(a4)
+addi a5,a0,0
+slli a4,a5,2
+add a5,t1,a4
+fsw ft0,0(a5)
+addi a4,a0,0
+slli a5,a4,2
+add a4,t0,a5
+fsw ft0,0(a4)
+addiw a4,a0,1
+mv a0,a4
+j .Lmain_cond0
+.Lmain_final2_split2:
+call thrd_join
+addi t1,sp,108
+li a0,4
+flw ft4,0(t1)
+addi t0,s0,-136
+flw ft3,0(t0)
+addi t1,s0,-208
+flw ft0,0(t1)
+addi t0,s0,-136
+flw fa0,4(t0)
+fmul.s ft1,ft3,ft4
+addi t1,s0,-136
+flw fa1,8(t1)
+addi t0,s0,-172
+fmul.s ft5,fa0,ft0
+fadd.s ft2,ft1,ft5
+flw ft1,0(t0)
+addi t0,s0,-160
+fmul.s ft6,fa1,ft1
+fadd.s ft5,ft2,ft6
+fsw ft5,0(t0)
+addi t0,sp,108
+flw ft5,4(t0)
+addi t0,s0,-208
+fmul.s ft2,ft3,ft5
+flw ft6,4(t0)
+addi t0,s0,-172
+fmul.s ft7,fa0,ft6
+fadd.s fs0,ft2,ft7
+flw ft2,4(t0)
+fmul.s fs1,fa1,ft2
+addi t0,s0,-160
+fadd.s ft7,fs0,fs1
+fsw ft7,4(t0)
+addi t0,sp,108
+flw ft7,8(t0)
+addi t0,s0,-208
+fmul.s fs1,ft3,ft7
+flw fs0,8(t0)
+addi t0,s0,-172
+fmul.s ft3,fa0,fs0
+fadd.s fa0,fs1,ft3
+flw ft3,8(t0)
+addi t0,s0,-160
+fmul.s fa2,fa1,ft3
+fadd.s fs1,fa0,fa2
+fsw fs1,8(t0)
+addi t0,s0,-196
+flw fs1,0(t0)
+addi t0,s0,-196
+fmul.s fa2,fs1,ft4
+flw fa0,4(t0)
+addi t0,s0,-196
+fmul.s fa3,fa0,ft0
+fadd.s fa1,fa2,fa3
+flw fa3,8(t0)
+addi t0,s0,-124
+fmul.s fa2,fa3,ft1
+fadd.s fa4,fa1,fa2
+fsw fa4,0(t0)
+fmul.s fa1,fs1,ft5
+addi t0,s0,-124
+fmul.s fa4,fa0,ft6
+fadd.s fa2,fa1,fa4
+fmul.s fa4,fa3,ft2
+fadd.s fa1,fa2,fa4
+fsw fa1,4(t0)
+addi t0,s0,-124
+fmul.s fa1,fs1,ft7
+fmul.s fs1,fa0,fs0
+fadd.s fa0,fa1,fs1
+fmul.s fs1,fa3,ft3
+fadd.s fa1,fa0,fs1
+fsw fa1,8(t0)
+addi t0,s0,-184
+flw fs1,0(t0)
+addi t0,s0,-184
+fmul.s fa0,fs1,ft4
+flw ft4,4(t0)
+fmul.s fa1,ft4,ft0
+addi t0,s0,-184
+fadd.s ft0,fa0,fa1
+flw fa1,8(t0)
+addi t0,s0,-112
+fmul.s fa0,fa1,ft1
+fadd.s ft1,ft0,fa0
+fmul.s ft0,fs1,ft5
+fsw ft1,0(t0)
+addi t0,s0,-112
+fmul.s ft5,ft4,ft6
+fadd.s ft1,ft0,ft5
+fmul.s ft5,fa1,ft2
+fmul.s ft2,ft4,fs0
+fadd.s ft0,ft1,ft5
+fsw ft0,4(t0)
+addi t0,s0,-112
+fmul.s ft0,fs1,ft7
+fadd.s ft1,ft0,ft2
+fmul.s ft2,fa1,ft3
+fadd.s ft0,ft1,ft2
+fsw ft0,8(t0)
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-160
+add s1,t0,t1
+call thrd_create
+mv t1,a0
+slliw t2,t1,0
+slliw t0,t1,2
+subw a0,t0,t2
+li t0,5
+addiw a1,a0,3
+div t1,a0,t0
+li t0,5
+div t2,a1,t0
+mv a1,t1
+j .Lmain_cond3
+.Lmain_cond3:
+slt t0,a1,t2
+bge a1,t2,.Lmain_final5
+j .Lmain_body4
+.Lmain_body4:
+addi t1,a1,0
+slli t0,t1,2
+add t1,s1,t0
+flw ft0,0(t1)
+fcvt.w.s t0,ft0,rtz
+sd t2,128(sp)
+sd a1,120(sp)
+mv a0,t0
+call putint
+ld t2,128(sp)
+ld a1,120(sp)
+addiw t0,a1,1
+mv a1,t0
+j .Lmain_cond3
+.Lmain_final5:
+call thrd_join
+li a0,10
+call putch
+addi t2,s0,-124
+addi t1,zero,0
+li a0,4
+slli t0,t1,2
+add t1,t2,t0
+sd t1,120(sp)
+call thrd_create
+mv t0,a0
+ld t1,120(sp)
+slliw s1,t0,0
+slliw t2,t0,2
+subw t0,t2,s1
+li t2,5
+div s1,t0,t2
+addiw t2,t0,3
+li t0,5
+div a1,t2,t0
+mv t0,s1
+j .Lmain_cond6
+.Lmain_cond6:
+slt t2,t0,a1
+bge t0,a1,.Lmain_final8
+j .Lmain_body7
+.Lmain_body7:
+addi t2,t0,0
+slli s1,t2,2
+add t2,t1,s1
+flw ft0,0(t2)
+sd t1,136(sp)
+fcvt.w.s t2,ft0,rtz
+sd t0,128(sp)
+mv a0,t2
+sd a1,120(sp)
+call putint
+ld a1,120(sp)
+ld t1,136(sp)
+ld t0,128(sp)
+addiw t2,t0,1
+mv t0,t2
+j .Lmain_cond6
+.Lmain_final8:
+call thrd_join
+li a0,10
+call putch
+li a0,4
+addi t1,zero,0
+slli t0,t1,2
+addi t1,s0,-112
+add t2,t1,t0
+sd t2,120(sp)
+call thrd_create
+ld t2,120(sp)
+mv s1,a0
+slliw t0,s1,2
+slliw t1,s1,0
+subw s1,t0,t1
+li t1,5
+addiw a0,s1,3
+div t0,s1,t1
+li s1,5
+div t1,a0,s1
+mv s1,t0
+j .Lmain_cond9
+.Lmain_cond9:
+slt t0,s1,t1
+bge s1,t1,.Lmain_exit
+j .Lmain_body10
+.Lmain_body10:
+addi a0,s1,0
+slli t0,a0,2
+add a0,t2,t0
+flw ft0,0(a0)
+fcvt.w.s t0,ft0,rtz
+sd t1,128(sp)
+sd t2,120(sp)
+mv a0,t0
+call putint
+ld t1,128(sp)
+addiw t0,s1,1
+ld t2,120(sp)
+mv s1,t0
+j .Lmain_cond9
+.Lmain_exit:
+call thrd_join
+li a0,10
+call putch
+ld ra,-8(s0)
+addiw a0,zero,0
+fld fs0,160(sp)
+fld fs1,176(sp)
+ld s1,168(sp)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm/99_matrix_tran.s b/quick_test/asm/99_matrix_tran.s
new file mode 100644
index 0000000..cdc4fe6
--- /dev/null
+++ b/quick_test/asm/99_matrix_tran.s
@@ -0,0 +1,301 @@
+.file "test.c"
+.option pic
+.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+.attribute unaligned_access, 0
+.attribute stack_align, 16
+.data
+.align	2
+.globl	M
+.type	M, @object
+.size	M, 4
+M:
+.word	0
+.data
+.align	2
+.globl	L
+.type	L, @object
+.size	L, 4
+L:
+.word	0
+.data
+.align	2
+.globl	N
+.type	N, @object
+.size	N, 4
+N:
+.word	0
+.text
+.align	3
+.globl	main
+.type	main, @function
+main:
+.Lmain_entry:
+lla t1,N
+li t0,3
+sd s0,-16(sp)
+sw t0,0(t1)
+mv s0,sp
+li t0,3
+addi a0,s0,-132
+addi t2,s0,-108
+lla t1,M
+sw t0,0(t1)
+addi sp,sp,-192
+sd ra,-8(s0)
+addi a2,s0,-144
+li t0,3
+lla t1,L
+sw t0,0(t1)
+sd s1,160(sp)
+addi t0,zero,0
+slli t1,t0,2
+addi s1,s0,-180
+addi t0,s0,-120
+add a1,t0,t1
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-192
+add a3,t0,t1
+addi t0,zero,0
+sd a3,152(sp)
+slli t1,t0,2
+add t0,t2,t1
+addi t1,zero,0
+slli t2,t1,2
+add t1,s1,t2
+sd t1,144(sp)
+addi t2,zero,0
+slli s1,t2,2
+add t2,a0,s1
+addi s1,zero,0
+sd t2,136(sp)
+slli a0,s1,2
+add s1,a2,a0
+sd a1,128(sp)
+li a0,4
+sd t0,120(sp)
+call thrd_create
+ld t1,144(sp)
+mv a2,a0
+ld a1,128(sp)
+slliw a0,a2,0
+ld t2,136(sp)
+slliw a4,a2,2
+subw a2,a4,a0
+ld a3,152(sp)
+li a0,5
+ld t0,120(sp)
+addiw a4,a2,3
+div a5,a2,a0
+li a0,5
+div a2,a4,a0
+mv a0,a5
+j .Lmain_cond0
+.Lmain_cond0:
+slt a4,a0,a2
+bge a0,a2,.Lmain_final2_split2
+j .Lmain_body1
+.Lmain_body1:
+fcvt.s.w ft0,a0
+addi a5,a0,0
+slli a4,a5,2
+add a5,t1,a4
+addi a4,a0,0
+fsw ft0,0(a5)
+slli a5,a4,2
+add a4,a3,a5
+fsw ft0,0(a4)
+addi a5,a0,0
+slli a4,a5,2
+add a5,t0,a4
+fsw ft0,0(a5)
+addi a4,a0,0
+slli a5,a4,2
+add a4,t2,a5
+fsw ft0,0(a4)
+addi a5,a0,0
+slli a4,a5,2
+add a5,s1,a4
+fsw ft0,0(a5)
+addi a4,a0,0
+slli a5,a4,2
+add a4,a1,a5
+fsw ft0,0(a4)
+addiw a4,a0,1
+mv a0,a4
+j .Lmain_cond0
+.Lmain_final2_split2:
+call thrd_join
+addi t2,s0,-168
+addi t1,s0,-96
+addi t0,s0,-108
+li a0,4
+flw ft0,4(t0)
+addi t0,s0,-192
+fsw ft0,8(t1)
+flw ft0,8(t0)
+addi t1,sp,108
+fsw ft0,4(t1)
+addi t0,s0,-168
+addi t1,s0,-192
+flw ft0,0(t1)
+fsw ft0,4(t0)
+addi t1,s0,-108
+addi t0,s0,-168
+flw ft0,0(t1)
+fsw ft0,8(t0)
+addi t1,s0,-96
+addi t0,s0,-180
+flw ft0,4(t0)
+addi t0,s0,-180
+fsw ft0,0(t1)
+addi t1,sp,108
+flw ft0,8(t0)
+fsw ft0,0(t1)
+addi t0,s0,-96
+addi t1,s0,-192
+flw ft0,4(t1)
+fsw ft0,4(t0)
+addi t1,s0,-108
+addi t0,sp,108
+flw ft0,8(t1)
+addi t1,s0,-168
+fsw ft0,8(t0)
+addi t0,s0,-180
+flw ft0,0(t0)
+fsw ft0,0(t1)
+addi t1,zero,0
+slli t0,t1,2
+add t1,t2,t0
+sd t1,120(sp)
+call thrd_create
+ld t1,120(sp)
+mv t2,a0
+slliw s1,t2,2
+slliw t0,t2,0
+subw t2,s1,t0
+addiw s1,t2,3
+li t0,5
+div a0,t2,t0
+li t0,5
+div a1,s1,t0
+mv t0,a0
+j .Lmain_cond3
+.Lmain_cond3:
+slt t2,t0,a1
+bge t0,a1,.Lmain_final5
+j .Lmain_body4
+.Lmain_body4:
+addi t2,t0,0
+slli s1,t2,2
+add t2,t1,s1
+flw ft0,0(t2)
+fcvt.w.s t2,ft0,rtz
+sd t1,136(sp)
+sd t0,128(sp)
+mv a0,t2
+sd a1,120(sp)
+call putint
+ld t1,136(sp)
+ld t0,128(sp)
+ld a1,120(sp)
+addiw t2,t0,1
+mv t0,t2
+j .Lmain_cond3
+.Lmain_final5:
+call thrd_join
+li a0,10
+call putch
+li a0,4
+addi t0,zero,0
+slli t1,t0,2
+addi t0,s0,-96
+add s1,t0,t1
+call thrd_create
+mv t0,a0
+slliw a0,t0,2
+slliw t1,t0,0
+subw t2,a0,t1
+addiw a0,t2,3
+li t1,5
+div t0,t2,t1
+li t2,5
+div t1,a0,t2
+mv t2,t0
+j .Lmain_cond6
+.Lmain_cond6:
+slt t0,t2,t1
+bge t2,t1,.Lmain_final8
+j .Lmain_body7
+.Lmain_body7:
+addi a0,t2,0
+slli t0,a0,2
+add a0,s1,t0
+flw ft0,0(a0)
+sd t1,128(sp)
+fcvt.w.s t0,ft0,rtz
+sd t2,120(sp)
+mv a0,t0
+call putint
+ld t1,128(sp)
+ld t2,120(sp)
+addiw t0,t2,1
+mv t2,t0
+j .Lmain_cond6
+.Lmain_final8:
+call thrd_join
+li a0,10
+call putch
+addi t0,zero,0
+li a0,4
+slli t1,t0,2
+addi t0,sp,108
+add a1,t0,t1
+sd a1,120(sp)
+call thrd_create
+ld a1,120(sp)
+mv t1,a0
+slliw t0,t1,0
+slliw t2,t1,2
+subw s1,t2,t0
+li t0,5
+addiw a0,s1,3
+div t1,s1,t0
+li t0,5
+div t2,a0,t0
+mv t0,t1
+j .Lmain_cond9
+.Lmain_cond9:
+slt t1,t0,t2
+bge t0,t2,.Lmain_exit
+j .Lmain_body10
+.Lmain_body10:
+addi t1,t0,0
+slli s1,t1,2
+add t1,a1,s1
+flw ft0,0(t1)
+fcvt.w.s t1,ft0,rtz
+sd t0,136(sp)
+sd t2,128(sp)
+mv a0,t1
+sd a1,120(sp)
+call putint
+ld a1,120(sp)
+ld t2,128(sp)
+ld t0,136(sp)
+addiw t1,t0,1
+mv t0,t1
+j .Lmain_cond9
+.Lmain_exit:
+call thrd_join
+li a0,10
+call putch
+ld ra,-8(s0)
+addiw a0,zero,0
+ld s1,160(sp)
+mv sp,s0
+ld s0,-16(s0)
+ret
+.size	main, .-main
+.ident	"compiler: (visionfive2) 0.1.0"
+.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/asm2bin.toml b/quick_test/asm2bin.toml
new file mode 100644
index 0000000..e20cc21
--- /dev/null
+++ b/quick_test/asm2bin.toml
@@ -0,0 +1,72 @@
+start_time = "2024-08-19 10:48:36.108676300 +08:00"
+end_time = "2024-08-19 10:48:36.424910880 +08:00"
+time_cost = "PT0.31623458S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/3.s"
+bin_path = "./sysy-data/quick_test/bin/3"
+start_time = "2024-08-19 10:48:36.154342630 +08:00"
+end_time = "2024-08-19 10:48:36.200659359 +08:00"
+time_cost = "PT0.046316729S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/6.s"
+bin_path = "./sysy-data/quick_test/bin/6"
+start_time = "2024-08-19 10:48:36.294797714 +08:00"
+end_time = "2024-08-19 10:48:36.340602354 +08:00"
+time_cost = "PT0.04580464S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/7.s"
+bin_path = "./sysy-data/quick_test/bin/7"
+start_time = "2024-08-19 10:48:36.251118613 +08:00"
+end_time = "2024-08-19 10:48:36.293606709 +08:00"
+time_cost = "PT0.042488096S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/96_matrix_add.s"
+bin_path = "./sysy-data/quick_test/bin/96_matrix_add"
+start_time = "2024-08-19 10:48:36.202477680 +08:00"
+end_time = "2024-08-19 10:48:36.249284425 +08:00"
+time_cost = "PT0.046806745S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/97_matrix_sub.s"
+bin_path = "./sysy-data/quick_test/bin/97_matrix_sub"
+start_time = "2024-08-19 10:48:36.342485420 +08:00"
+end_time = "2024-08-19 10:48:36.386292175 +08:00"
+time_cost = "PT0.043806755S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/98_matrix_mul.s"
+bin_path = "./sysy-data/quick_test/bin/98_matrix_mul"
+start_time = "2024-08-19 10:48:36.109906116 +08:00"
+end_time = "2024-08-19 10:48:36.152774993 +08:00"
+time_cost = "PT0.042868877S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/asm/99_matrix_tran.s"
+bin_path = "./sysy-data/quick_test/bin/99_matrix_tran"
+start_time = "2024-08-19 10:48:36.387394276 +08:00"
+end_time = "2024-08-19 10:48:36.424825872 +08:00"
+time_cost = "PT0.037431596S"
+success = true
+per_timeout = false
diff --git a/quick_test/bin/3 b/quick_test/bin/3
new file mode 100755
index 0000000..09533df
Binary files /dev/null and b/quick_test/bin/3 differ
diff --git a/quick_test/bin/6 b/quick_test/bin/6
new file mode 100755
index 0000000..8086ae7
Binary files /dev/null and b/quick_test/bin/6 differ
diff --git a/quick_test/bin/7 b/quick_test/bin/7
new file mode 100755
index 0000000..e2d4735
Binary files /dev/null and b/quick_test/bin/7 differ
diff --git a/quick_test/bin/96_matrix_add b/quick_test/bin/96_matrix_add
new file mode 100755
index 0000000..2bcf607
Binary files /dev/null and b/quick_test/bin/96_matrix_add differ
diff --git a/quick_test/bin/97_matrix_sub b/quick_test/bin/97_matrix_sub
new file mode 100755
index 0000000..c300e12
Binary files /dev/null and b/quick_test/bin/97_matrix_sub differ
diff --git a/quick_test/bin/98_matrix_mul b/quick_test/bin/98_matrix_mul
new file mode 100755
index 0000000..4abbc10
Binary files /dev/null and b/quick_test/bin/98_matrix_mul differ
diff --git a/quick_test/bin/99_matrix_tran b/quick_test/bin/99_matrix_tran
new file mode 100755
index 0000000..c52fa4f
Binary files /dev/null and b/quick_test/bin/99_matrix_tran differ
diff --git a/quick_test/compile.toml b/quick_test/compile.toml
new file mode 100644
index 0000000..de2249d
--- /dev/null
+++ b/quick_test/compile.toml
@@ -0,0 +1,72 @@
+start_time = "2024-08-19 10:48:35.917414358 +08:00"
+end_time = "2024-08-19 10:48:36.100441947 +08:00"
+time_cost = "PT0.183027589S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/3.sy"
+asm = "./sysy-data/quick_test/asm/3.s"
+start_time = "2024-08-19 10:48:36.023498273 +08:00"
+end_time = "2024-08-19 10:48:36.038450057 +08:00"
+time_cost = "PT0.014951784S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/6.sy"
+asm = "./sysy-data/quick_test/asm/6.s"
+start_time = "2024-08-19 10:48:36.011369803 +08:00"
+end_time = "2024-08-19 10:48:36.022157891 +08:00"
+time_cost = "PT0.010788088S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/7.sy"
+asm = "./sysy-data/quick_test/asm/7.s"
+start_time = "2024-08-19 10:48:36.039594228 +08:00"
+end_time = "2024-08-19 10:48:36.052244250 +08:00"
+time_cost = "PT0.012650022S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/96_matrix_add.sy"
+asm = "./sysy-data/quick_test/asm/96_matrix_add.s"
+start_time = "2024-08-19 10:48:35.991482933 +08:00"
+end_time = "2024-08-19 10:48:36.010398249 +08:00"
+time_cost = "PT0.018915316S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/97_matrix_sub.sy"
+asm = "./sysy-data/quick_test/asm/97_matrix_sub.s"
+start_time = "2024-08-19 10:48:35.918738774 +08:00"
+end_time = "2024-08-19 10:48:35.954823062 +08:00"
+time_cost = "PT0.036084288S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/98_matrix_mul.sy"
+asm = "./sysy-data/quick_test/asm/98_matrix_mul.s"
+start_time = "2024-08-19 10:48:36.053876120 +08:00"
+end_time = "2024-08-19 10:48:36.100244879 +08:00"
+time_cost = "PT0.046368759S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/99_matrix_tran.sy"
+asm = "./sysy-data/quick_test/asm/99_matrix_tran.s"
+start_time = "2024-08-19 10:48:35.956222772 +08:00"
+end_time = "2024-08-19 10:48:35.989595600 +08:00"
+time_cost = "PT0.033372828S"
+success = true
+per_timeout = false
diff --git a/quick_test/diff.toml b/quick_test/diff.toml
new file mode 100644
index 0000000..f9197a9
--- /dev/null
+++ b/quick_test/diff.toml
@@ -0,0 +1,63 @@
+start_time = "2024-08-19 10:48:37.928981007 +08:00"
+end_time = "2024-08-19 10:48:37.942229844 +08:00"
+time_cost = "PT0.013248837S"
+all_success = false
+success_num = 3
+failed_num = 4
+total_num = 7
+
+[[diff]]
+out = "./sysy-data/quick_test/output/6.out"
+expect_out = "./sysy-data/quick_test/expect/output/6.out"
+start_time = "2024-08-19 10:48:37.929759352 +08:00"
+end_time = "2024-08-19 10:48:37.930398286 +08:00"
+time_cost = "PT0.000638934S"
+status = "Same"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/99_matrix_tran.out"
+expect_out = "./sysy-data/quick_test/expect/output/99_matrix_tran.out"
+start_time = "2024-08-19 10:48:37.931092818 +08:00"
+end_time = "2024-08-19 10:48:37.931918325 +08:00"
+time_cost = "PT0.000825507S"
+status = "Different"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/7.out"
+expect_out = "./sysy-data/quick_test/expect/output/7.out"
+start_time = "2024-08-19 10:48:37.934823461 +08:00"
+end_time = "2024-08-19 10:48:37.935734433 +08:00"
+time_cost = "PT0.000910972S"
+status = "Same"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/96_matrix_add.out"
+expect_out = "./sysy-data/quick_test/expect/output/96_matrix_add.out"
+start_time = "2024-08-19 10:48:37.932973661 +08:00"
+end_time = "2024-08-19 10:48:37.933633292 +08:00"
+time_cost = "PT0.000659631S"
+status = "Different"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/98_matrix_mul.out"
+expect_out = "./sysy-data/quick_test/expect/output/98_matrix_mul.out"
+start_time = "2024-08-19 10:48:37.939581326 +08:00"
+end_time = "2024-08-19 10:48:37.940228658 +08:00"
+time_cost = "PT0.000647332S"
+status = "Different"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/97_matrix_sub.out"
+expect_out = "./sysy-data/quick_test/expect/output/97_matrix_sub.out"
+start_time = "2024-08-19 10:48:37.941393583 +08:00"
+end_time = "2024-08-19 10:48:37.942192165 +08:00"
+time_cost = "PT0.000798582S"
+status = "Different"
+
+[[diff]]
+out = "./sysy-data/quick_test/output/3.out"
+expect_out = "./sysy-data/quick_test/expect/output/3.out"
+start_time = "2024-08-19 10:48:37.936767361 +08:00"
+end_time = "2024-08-19 10:48:37.937957244 +08:00"
+time_cost = "PT0.001189883S"
+status = "Same"
diff --git a/quick_test/diff/3.diff b/quick_test/diff/3.diff
new file mode 100644
index 0000000..e69de29
diff --git a/quick_test/diff/6.diff b/quick_test/diff/6.diff
new file mode 100644
index 0000000..e69de29
diff --git a/quick_test/diff/7.diff b/quick_test/diff/7.diff
new file mode 100644
index 0000000..e69de29
diff --git a/quick_test/diff/96_matrix_add.diff b/quick_test/diff/96_matrix_add.diff
new file mode 100644
index 0000000..8e92ce8
--- /dev/null
+++ b/quick_test/diff/96_matrix_add.diff
@@ -0,0 +1,10 @@
+0a1,3
+> 024
+> 024
+> 024
+2c5
+< ExitStatus(unix_wait_status(139))
+\ No newline at end of file
+---
+> 0
+\ No newline at end of file
diff --git a/quick_test/diff/97_matrix_sub.diff b/quick_test/diff/97_matrix_sub.diff
new file mode 100644
index 0000000..ed0c152
--- /dev/null
+++ b/quick_test/diff/97_matrix_sub.diff
@@ -0,0 +1,10 @@
+0a1,3
+> 000
+> 000
+> 000
+2c5
+< ExitStatus(unix_wait_status(139))
+\ No newline at end of file
+---
+> 0
+\ No newline at end of file
diff --git a/quick_test/diff/98_matrix_mul.diff b/quick_test/diff/98_matrix_mul.diff
new file mode 100644
index 0000000..855f874
--- /dev/null
+++ b/quick_test/diff/98_matrix_mul.diff
@@ -0,0 +1,10 @@
+0a1,3
+> 036
+> 036
+> 036
+2c5
+< ExitStatus(unix_wait_status(139))
+\ No newline at end of file
+---
+> 0
+\ No newline at end of file
diff --git a/quick_test/diff/99_matrix_tran.diff b/quick_test/diff/99_matrix_tran.diff
new file mode 100644
index 0000000..48674fe
--- /dev/null
+++ b/quick_test/diff/99_matrix_tran.diff
@@ -0,0 +1,10 @@
+0a1,3
+> 000
+> 111
+> 222
+2c5
+< ExitStatus(unix_wait_status(139))
+\ No newline at end of file
+---
+> 0
+\ No newline at end of file
diff --git a/quick_test/execute.toml b/quick_test/execute.toml
new file mode 100644
index 0000000..b3bed96
--- /dev/null
+++ b/quick_test/execute.toml
@@ -0,0 +1,79 @@
+start_time = "2024-08-19 10:48:36.430522756 +08:00"
+end_time = "2024-08-19 10:48:37.908763935 +08:00"
+time_cost = "PT1.478241179S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/3"
+input_path = "./sysy-data/quick_test/input/3.in"
+output_path = "./sysy-data/quick_test/output/3.out"
+start_time = "2024-08-19 10:48:37.882813716 +08:00"
+end_time = "2024-08-19 10:48:37.908638058 +08:00"
+time_cost = "PT0.025824342S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/6"
+input_path = "./sysy-data/quick_test/input/6.in"
+output_path = "./sysy-data/quick_test/output/6.out"
+start_time = "2024-08-19 10:48:37.155747910 +08:00"
+end_time = "2024-08-19 10:48:37.178043778 +08:00"
+time_cost = "PT0.022295868S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/7"
+input_path = "./sysy-data/quick_test/input/7.in"
+output_path = "./sysy-data/quick_test/output/7.out"
+start_time = "2024-08-19 10:48:37.514335137 +08:00"
+end_time = "2024-08-19 10:48:37.544210775 +08:00"
+time_cost = "PT0.029875638S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/96_matrix_add"
+input_path = "./sysy-data/quick_test/input/96_matrix_add.in"
+output_path = "./sysy-data/quick_test/output/96_matrix_add.out"
+start_time = "2024-08-19 10:48:36.432267300 +08:00"
+end_time = "2024-08-19 10:48:36.774847170 +08:00"
+time_cost = "PT0.34257987S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/97_matrix_sub"
+input_path = "./sysy-data/quick_test/input/97_matrix_sub.in"
+output_path = "./sysy-data/quick_test/output/97_matrix_sub.out"
+start_time = "2024-08-19 10:48:37.545762887 +08:00"
+end_time = "2024-08-19 10:48:37.881000271 +08:00"
+time_cost = "PT0.335237384S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/98_matrix_mul"
+input_path = "./sysy-data/quick_test/input/98_matrix_mul.in"
+output_path = "./sysy-data/quick_test/output/98_matrix_mul.out"
+start_time = "2024-08-19 10:48:36.776139802 +08:00"
+end_time = "2024-08-19 10:48:37.153948244 +08:00"
+time_cost = "PT0.377808442S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/bin/99_matrix_tran"
+input_path = "./sysy-data/quick_test/input/99_matrix_tran.in"
+output_path = "./sysy-data/quick_test/output/99_matrix_tran.out"
+start_time = "2024-08-19 10:48:37.179460152 +08:00"
+end_time = "2024-08-19 10:48:37.513118892 +08:00"
+time_cost = "PT0.33365874S"
+per_timeout = false
+success = true
diff --git a/quick_test/expect/asm/3.s b/quick_test/expect/asm/3.s
new file mode 100644
index 0000000..641dedb
--- /dev/null
+++ b/quick_test/expect/asm/3.s
@@ -0,0 +1,79 @@
+	.file	"3.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	A
+	.bss
+	.align	3
+	.type	A, @object
+	.size	A, 36
+A:
+	.zero	36
+	.globl	B
+	.align	3
+	.type	B, @object
+	.size	B, 36
+B:
+	.zero	36
+	.text
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB6:
+	.cfi_startproc
+	addi	sp,sp,-32
+	.cfi_def_cfa_offset 32
+	sd	ra,24(sp)
+	sd	s0,16(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,32
+	.cfi_def_cfa 8, 0
+	sw	zero,-20(s0)
+	lui	a5,%hi(A)
+	addi	a0,a5,%lo(A)
+	call	getarray
+	j	.L2
+.L3:
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+	lui	a5,%hi(A)
+	addi	a4,a5,%lo(A)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a4,a5
+	lw	a4,0(a5)
+	lui	a5,%hi(B)
+	addi	a3,a5,%lo(B)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a3,a5
+	sw	a4,0(a5)
+.L2:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,7
+	ble	a4,a5,.L3
+	lui	a5,%hi(B)
+	addi	a1,a5,%lo(B)
+	li	a0,8
+	call	putarray
+	li	a5,0
+	mv	a0,a5
+	ld	ra,24(sp)
+	.cfi_restore 1
+	ld	s0,16(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 32
+	addi	sp,sp,32
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE6:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/6.s b/quick_test/expect/asm/6.s
new file mode 100644
index 0000000..eee5ce8
--- /dev/null
+++ b/quick_test/expect/asm/6.s
@@ -0,0 +1,76 @@
+	.file	"6.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	A
+	.data
+	.align	3
+	.type	A, @object
+	.size	A, 36
+A:
+	.word	1
+	.word	1
+	.word	4
+	.word	5
+	.word	1
+	.word	4
+	.zero	12
+	.text
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB6:
+	.cfi_startproc
+	addi	sp,sp,-32
+	.cfi_def_cfa_offset 32
+	sd	ra,24(sp)
+	sd	s0,16(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,32
+	.cfi_def_cfa 8, 0
+	lui	a5,%hi(A)
+	addi	a5,a5,%lo(A)
+	li	a4,11
+	sw	a4,0(a5)
+	li	a0,4
+	call	thrd_create
+	mv	a5,a0
+	sw	a5,-20(s0)
+	lui	a5,%hi(A)
+	addi	a4,a5,%lo(A)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a4,a5
+	lw	a5,0(a5)
+	slliw	a5,a5,1
+	sext.w	a4,a5
+	lui	a5,%hi(A)
+	addi	a3,a5,%lo(A)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a3,a5
+	sw	a4,0(a5)
+	call	thrd_join
+	lui	a5,%hi(A)
+	addi	a1,a5,%lo(A)
+	li	a0,8
+	call	putarray
+	li	a5,0
+	mv	a0,a5
+	ld	ra,24(sp)
+	.cfi_restore 1
+	ld	s0,16(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 32
+	addi	sp,sp,32
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE6:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/7.s b/quick_test/expect/asm/7.s
new file mode 100644
index 0000000..91b0bad
--- /dev/null
+++ b/quick_test/expect/asm/7.s
@@ -0,0 +1,95 @@
+	.file	"7.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	A
+	.data
+	.align	3
+	.type	A, @object
+	.size	A, 36
+A:
+	.word	1
+	.word	1
+	.word	4
+	.word	5
+	.word	1
+	.word	4
+	.zero	12
+	.text
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB6:
+	.cfi_startproc
+	addi	sp,sp,-32
+	.cfi_def_cfa_offset 32
+	sd	ra,24(sp)
+	sd	s0,16(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,32
+	.cfi_def_cfa 8, 0
+	li	a0,4
+	call	thrd_create
+	mv	a5,a0
+	sw	a5,-20(s0)
+	lui	a5,%hi(A)
+	addi	a4,a5,%lo(A)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a4,a5
+	lw	a5,0(a5)
+	slliw	a5,a5,1
+	sext.w	a4,a5
+	lui	a5,%hi(A)
+	addi	a3,a5,%lo(A)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	add	a5,a3,a5
+	sw	a4,0(a5)
+	call	thrd_join
+	lui	a5,%hi(A)
+	addi	a1,a5,%lo(A)
+	li	a0,8
+	call	putarray
+	li	a0,4
+	call	thrd_create
+	mv	a5,a0
+	sw	a5,-24(s0)
+	lui	a5,%hi(A)
+	addi	a4,a5,%lo(A)
+	lw	a5,-24(s0)
+	slli	a5,a5,2
+	add	a5,a4,a5
+	lw	a5,0(a5)
+	slliw	a5,a5,1
+	sext.w	a4,a5
+	lui	a5,%hi(A)
+	addi	a3,a5,%lo(A)
+	lw	a5,-24(s0)
+	slli	a5,a5,2
+	add	a5,a3,a5
+	sw	a4,0(a5)
+	call	thrd_join
+	lui	a5,%hi(A)
+	addi	a1,a5,%lo(A)
+	li	a0,8
+	call	putarray
+	li	a5,0
+	mv	a0,a5
+	ld	ra,24(sp)
+	.cfi_restore 1
+	ld	s0,16(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 32
+	addi	sp,sp,32
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE6:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/96_matrix_add.s b/quick_test/expect/asm/96_matrix_add.s
new file mode 100644
index 0000000..ea6c4d5
--- /dev/null
+++ b/quick_test/expect/asm/96_matrix_add.s
@@ -0,0 +1,303 @@
+	.file	"96_matrix_add.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	M
+	.section	.sbss,"aw",@nobits
+	.align	2
+	.type	M, @object
+	.size	M, 4
+M:
+	.zero	4
+	.globl	L
+	.align	2
+	.type	L, @object
+	.size	L, 4
+L:
+	.zero	4
+	.globl	N
+	.align	2
+	.type	N, @object
+	.size	N, 4
+N:
+	.zero	4
+	.text
+	.align	1
+	.globl	add
+	.type	add, @function
+add:
+.LFB0:
+	.cfi_startproc
+	addi	sp,sp,-96
+	.cfi_def_cfa_offset 96
+	sd	s0,88(sp)
+	.cfi_offset 8, -8
+	addi	s0,sp,96
+	.cfi_def_cfa 8, 0
+	sd	a0,-40(s0)
+	sd	a1,-48(s0)
+	sd	a2,-56(s0)
+	sd	a3,-64(s0)
+	sd	a4,-72(s0)
+	sd	a5,-80(s0)
+	sd	a6,-88(s0)
+	sd	a7,-96(s0)
+	sw	zero,-20(s0)
+	j	.L2
+.L3:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-40(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-64(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-88(s0)
+	add	a5,a4,a5
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-48(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-72(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-96(s0)
+	add	a5,a4,a5
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-56(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-80(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,0(s0)
+	add	a5,a4,a5
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L2:
+	lui	a5,%hi(M)
+	lw	a4,%lo(M)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L3
+	li	a5,0
+	mv	a0,a5
+	ld	s0,88(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 96
+	addi	sp,sp,96
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE0:
+	.size	add, .-add
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB1:
+	.cfi_startproc
+	addi	sp,sp,-192
+	.cfi_def_cfa_offset 192
+	sd	ra,184(sp)
+	sd	s0,176(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,192
+	.cfi_def_cfa 8, 0
+	lui	a5,%hi(N)
+	li	a4,3
+	sw	a4,%lo(N)(a5)
+	lui	a5,%hi(M)
+	li	a4,3
+	sw	a4,%lo(M)(a5)
+	lui	a5,%hi(L)
+	li	a4,3
+	sw	a4,%lo(L)(a5)
+	sw	zero,-20(s0)
+	j	.L6
+.L7:
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-24(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-40(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-56(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-72(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-88(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-104(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L6:
+	lui	a5,%hi(M)
+	lw	a4,%lo(M)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L7
+	addi	a7,s0,-160
+	addi	a6,s0,-144
+	addi	t1,s0,-120
+	addi	a4,s0,-104
+	addi	a3,s0,-88
+	addi	a2,s0,-72
+	addi	a1,s0,-56
+	addi	a0,s0,-40
+	addi	a5,s0,-176
+	sd	a5,0(sp)
+	mv	a5,t1
+	call	add
+	mv	a5,a0
+	sw	a5,-20(s0)
+	j	.L8
+.L9:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-128(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L8:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L9
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	sw	zero,-20(s0)
+	j	.L10
+.L11:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-144(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L10:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L11
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	sw	zero,-20(s0)
+	j	.L12
+.L13:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-160(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L12:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L13
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	li	a5,0
+	mv	a0,a5
+	ld	ra,184(sp)
+	.cfi_restore 1
+	ld	s0,176(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 192
+	addi	sp,sp,192
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE1:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/97_matrix_sub.s b/quick_test/expect/asm/97_matrix_sub.s
new file mode 100644
index 0000000..57d8033
--- /dev/null
+++ b/quick_test/expect/asm/97_matrix_sub.s
@@ -0,0 +1,298 @@
+	.file	"97_matrix_sub.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	N
+	.section	.sbss,"aw",@nobits
+	.align	2
+	.type	N, @object
+	.size	N, 4
+N:
+	.zero	4
+	.globl	M
+	.align	2
+	.type	M, @object
+	.size	M, 4
+M:
+	.zero	4
+	.globl	L
+	.align	2
+	.type	L, @object
+	.size	L, 4
+L:
+	.zero	4
+	.text
+	.align	1
+	.globl	sub
+	.type	sub, @function
+sub:
+.LFB0:
+	.cfi_startproc
+	addi	sp,sp,-96
+	.cfi_def_cfa_offset 96
+	sd	s0,88(sp)
+	.cfi_offset 8, -8
+	addi	s0,sp,96
+	.cfi_def_cfa 8, 0
+	sd	a0,-40(s0)
+	sd	a1,-48(s0)
+	sd	a2,-56(s0)
+	sd	a3,-64(s0)
+	sd	a4,-72(s0)
+	sd	a5,-80(s0)
+	sd	a6,-88(s0)
+	sd	a7,-96(s0)
+	sw	zero,-20(s0)
+	j	.L2
+.L3:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-40(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-64(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-88(s0)
+	add	a5,a4,a5
+	fsub.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-48(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-72(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-96(s0)
+	add	a5,a4,a5
+	fsub.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-56(s0)
+	add	a5,a4,a5
+	flw	fa4,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,-80(s0)
+	add	a5,a4,a5
+	flw	fa5,0(a5)
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	ld	a4,0(s0)
+	add	a5,a4,a5
+	fsub.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L2:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,2
+	ble	a4,a5,.L3
+	li	a5,0
+	mv	a0,a5
+	ld	s0,88(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 96
+	addi	sp,sp,96
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE0:
+	.size	sub, .-sub
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB1:
+	.cfi_startproc
+	addi	sp,sp,-192
+	.cfi_def_cfa_offset 192
+	sd	ra,184(sp)
+	sd	s0,176(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,192
+	.cfi_def_cfa 8, 0
+	lui	a5,%hi(N)
+	li	a4,3
+	sw	a4,%lo(N)(a5)
+	lui	a5,%hi(M)
+	li	a4,3
+	sw	a4,%lo(M)(a5)
+	lui	a5,%hi(L)
+	li	a4,3
+	sw	a4,%lo(L)(a5)
+	sw	zero,-20(s0)
+	j	.L6
+.L7:
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-24(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-40(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-56(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-72(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-88(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-104(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L6:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,2
+	ble	a4,a5,.L7
+	addi	a7,s0,-160
+	addi	a6,s0,-144
+	addi	t1,s0,-120
+	addi	a4,s0,-104
+	addi	a3,s0,-88
+	addi	a2,s0,-72
+	addi	a1,s0,-56
+	addi	a0,s0,-40
+	addi	a5,s0,-176
+	sd	a5,0(sp)
+	mv	a5,t1
+	call	sub
+	mv	a5,a0
+	sw	a5,-20(s0)
+	j	.L8
+.L9:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-128(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L8:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,2
+	ble	a4,a5,.L9
+	li	a5,10
+	sw	a5,-24(s0)
+	sw	zero,-20(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	j	.L10
+.L11:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-144(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L10:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,2
+	ble	a4,a5,.L11
+	li	a5,10
+	sw	a5,-24(s0)
+	sw	zero,-20(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	j	.L12
+.L13:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-160(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L12:
+	lw	a5,-20(s0)
+	sext.w	a4,a5
+	li	a5,2
+	ble	a4,a5,.L13
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	li	a5,0
+	mv	a0,a5
+	ld	ra,184(sp)
+	.cfi_restore 1
+	ld	s0,176(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 192
+	addi	sp,sp,192
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE1:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/98_matrix_mul.s b/quick_test/expect/asm/98_matrix_mul.s
new file mode 100644
index 0000000..958af4e
--- /dev/null
+++ b/quick_test/expect/asm/98_matrix_mul.s
@@ -0,0 +1,457 @@
+	.file	"98_matrix_mul.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	M
+	.section	.sbss,"aw",@nobits
+	.align	2
+	.type	M, @object
+	.size	M, 4
+M:
+	.zero	4
+	.globl	L
+	.align	2
+	.type	L, @object
+	.size	L, 4
+L:
+	.zero	4
+	.globl	N
+	.align	2
+	.type	N, @object
+	.size	N, 4
+N:
+	.zero	4
+	.text
+	.align	1
+	.globl	mul
+	.type	mul, @function
+mul:
+.LFB0:
+	.cfi_startproc
+	addi	sp,sp,-96
+	.cfi_def_cfa_offset 96
+	sd	s0,88(sp)
+	.cfi_offset 8, -8
+	addi	s0,sp,96
+	.cfi_def_cfa 8, 0
+	sd	a0,-40(s0)
+	sd	a1,-48(s0)
+	sd	a2,-56(s0)
+	sd	a3,-64(s0)
+	sd	a4,-72(s0)
+	sd	a5,-80(s0)
+	sd	a6,-88(s0)
+	sd	a7,-96(s0)
+	sw	zero,-20(s0)
+	ld	a5,-40(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa5,fa4,fa5
+	ld	a5,-88(s0)
+	fsw	fa5,0(a5)
+	ld	a5,-40(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,-88(s0)
+	addi	a5,a5,4
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	ld	a5,-40(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-40(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,-88(s0)
+	addi	a5,a5,8
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	ld	a5,-48(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa5,fa4,fa5
+	ld	a5,-96(s0)
+	fsw	fa5,0(a5)
+	ld	a5,-48(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,-96(s0)
+	addi	a5,a5,4
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	ld	a5,-48(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-48(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,-96(s0)
+	addi	a5,a5,8
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	ld	a5,-56(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa5,fa4,fa5
+	ld	a5,0(s0)
+	fsw	fa5,0(a5)
+	ld	a5,-56(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,4
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,0(s0)
+	addi	a5,a5,4
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	ld	a5,-56(s0)
+	flw	fa4,0(a5)
+	ld	a5,-64(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,4
+	flw	fa3,0(a5)
+	ld	a5,-72(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	fadd.s	fa4,fa4,fa5
+	ld	a5,-56(s0)
+	addi	a5,a5,8
+	flw	fa3,0(a5)
+	ld	a5,-80(s0)
+	addi	a5,a5,8
+	flw	fa5,0(a5)
+	fmul.s	fa5,fa3,fa5
+	ld	a5,0(s0)
+	addi	a5,a5,8
+	fadd.s	fa5,fa4,fa5
+	fsw	fa5,0(a5)
+	li	a5,0
+	mv	a0,a5
+	ld	s0,88(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 96
+	addi	sp,sp,96
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE0:
+	.size	mul, .-mul
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB1:
+	.cfi_startproc
+	addi	sp,sp,-192
+	.cfi_def_cfa_offset 192
+	sd	ra,184(sp)
+	sd	s0,176(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,192
+	.cfi_def_cfa 8, 0
+	lui	a5,%hi(N)
+	li	a4,3
+	sw	a4,%lo(N)(a5)
+	lui	a5,%hi(M)
+	li	a4,3
+	sw	a4,%lo(M)(a5)
+	lui	a5,%hi(L)
+	li	a4,3
+	sw	a4,%lo(L)(a5)
+	sw	zero,-20(s0)
+	j	.L4
+.L5:
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-24(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-40(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-56(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-72(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-88(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-104(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L4:
+	lui	a5,%hi(M)
+	lw	a4,%lo(M)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L5
+	addi	a7,s0,-160
+	addi	a6,s0,-144
+	addi	t1,s0,-120
+	addi	a4,s0,-104
+	addi	a3,s0,-88
+	addi	a2,s0,-72
+	addi	a1,s0,-56
+	addi	a0,s0,-40
+	addi	a5,s0,-176
+	sd	a5,0(sp)
+	mv	a5,t1
+	call	mul
+	mv	a5,a0
+	sw	a5,-20(s0)
+	j	.L6
+.L7:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-128(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L6:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L7
+	li	a5,10
+	sw	a5,-24(s0)
+	sw	zero,-20(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	j	.L8
+.L9:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-144(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L8:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L9
+	li	a5,10
+	sw	a5,-24(s0)
+	sw	zero,-20(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	j	.L10
+.L11:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-160(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L10:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L11
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	li	a5,0
+	mv	a0,a5
+	ld	ra,184(sp)
+	.cfi_restore 1
+	ld	s0,176(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 192
+	addi	sp,sp,192
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE1:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm/99_matrix_tran.s b/quick_test/expect/asm/99_matrix_tran.s
new file mode 100644
index 0000000..c6940bf
--- /dev/null
+++ b/quick_test/expect/asm/99_matrix_tran.s
@@ -0,0 +1,286 @@
+	.file	"99_matrix_tran.sy"
+	.option nopic
+	.attribute arch, "rv64i2p1_m2p0_a2p1_f2p2_d2p2_c2p0_zicsr2p0_zifencei2p0"
+	.attribute unaligned_access, 0
+	.attribute stack_align, 16
+	.text
+	.globl	M
+	.section	.sbss,"aw",@nobits
+	.align	2
+	.type	M, @object
+	.size	M, 4
+M:
+	.zero	4
+	.globl	L
+	.align	2
+	.type	L, @object
+	.size	L, 4
+L:
+	.zero	4
+	.globl	N
+	.align	2
+	.type	N, @object
+	.size	N, 4
+N:
+	.zero	4
+	.text
+	.align	1
+	.globl	tran
+	.type	tran, @function
+tran:
+.LFB0:
+	.cfi_startproc
+	addi	sp,sp,-96
+	.cfi_def_cfa_offset 96
+	sd	s0,88(sp)
+	.cfi_offset 8, -8
+	addi	s0,sp,96
+	.cfi_def_cfa 8, 0
+	sd	a0,-40(s0)
+	sd	a1,-48(s0)
+	sd	a2,-56(s0)
+	sd	a3,-64(s0)
+	sd	a4,-72(s0)
+	sd	a5,-80(s0)
+	sd	a6,-88(s0)
+	sd	a7,-96(s0)
+	sw	zero,-20(s0)
+	ld	a5,-96(s0)
+	addi	a5,a5,8
+	ld	a4,-56(s0)
+	flw	fa5,4(a4)
+	fsw	fa5,0(a5)
+	ld	a5,0(s0)
+	addi	a5,a5,4
+	ld	a4,-48(s0)
+	flw	fa5,8(a4)
+	fsw	fa5,0(a5)
+	ld	a5,-88(s0)
+	addi	a5,a5,4
+	ld	a4,-48(s0)
+	flw	fa5,0(a4)
+	fsw	fa5,0(a5)
+	ld	a5,-88(s0)
+	addi	a5,a5,8
+	ld	a4,-56(s0)
+	flw	fa5,0(a4)
+	fsw	fa5,0(a5)
+	ld	a5,-40(s0)
+	flw	fa5,4(a5)
+	ld	a5,-96(s0)
+	fsw	fa5,0(a5)
+	ld	a5,-40(s0)
+	flw	fa5,8(a5)
+	ld	a5,0(s0)
+	fsw	fa5,0(a5)
+	ld	a5,-96(s0)
+	addi	a5,a5,4
+	ld	a4,-48(s0)
+	flw	fa5,4(a4)
+	fsw	fa5,0(a5)
+	ld	a5,0(s0)
+	addi	a5,a5,8
+	ld	a4,-56(s0)
+	flw	fa5,8(a4)
+	fsw	fa5,0(a5)
+	ld	a5,-40(s0)
+	flw	fa5,0(a5)
+	ld	a5,-88(s0)
+	fsw	fa5,0(a5)
+	li	a5,0
+	mv	a0,a5
+	ld	s0,88(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 96
+	addi	sp,sp,96
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE0:
+	.size	tran, .-tran
+	.align	1
+	.globl	main
+	.type	main, @function
+main:
+.LFB1:
+	.cfi_startproc
+	addi	sp,sp,-192
+	.cfi_def_cfa_offset 192
+	sd	ra,184(sp)
+	sd	s0,176(sp)
+	.cfi_offset 1, -8
+	.cfi_offset 8, -16
+	addi	s0,sp,192
+	.cfi_def_cfa 8, 0
+	lui	a5,%hi(N)
+	li	a4,3
+	sw	a4,%lo(N)(a5)
+	lui	a5,%hi(M)
+	li	a4,3
+	sw	a4,%lo(M)(a5)
+	lui	a5,%hi(L)
+	li	a4,3
+	sw	a4,%lo(L)(a5)
+	sw	zero,-20(s0)
+	j	.L4
+.L5:
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-24(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-40(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-56(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-72(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-88(a5)
+	lw	a5,-20(s0)
+	fcvt.s.w	fa5,a5
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	fsw	fa5,-104(a5)
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L4:
+	lui	a5,%hi(M)
+	lw	a4,%lo(M)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L5
+	addi	a7,s0,-160
+	addi	a6,s0,-144
+	addi	t1,s0,-120
+	addi	a4,s0,-104
+	addi	a3,s0,-88
+	addi	a2,s0,-72
+	addi	a1,s0,-56
+	addi	a0,s0,-40
+	addi	a5,s0,-176
+	sd	a5,0(sp)
+	mv	a5,t1
+	call	tran
+	mv	a5,a0
+	sw	a5,-20(s0)
+	j	.L6
+.L7:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-128(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L6:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L7
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	sw	zero,-20(s0)
+	j	.L8
+.L9:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-144(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L8:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L9
+	li	a5,10
+	sw	a5,-24(s0)
+	sw	zero,-20(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	j	.L10
+.L11:
+	lw	a5,-20(s0)
+	slli	a5,a5,2
+	addi	a5,a5,-16
+	add	a5,a5,s0
+	flw	fa5,-160(a5)
+	fcvt.w.s a5,fa5,rtz
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putint
+	lw	a5,-20(s0)
+	addiw	a5,a5,1
+	sw	a5,-20(s0)
+.L10:
+	lui	a5,%hi(N)
+	lw	a4,%lo(N)(a5)
+	lw	a5,-20(s0)
+	sext.w	a5,a5
+	blt	a5,a4,.L11
+	li	a5,10
+	sw	a5,-24(s0)
+	lw	a5,-24(s0)
+	mv	a0,a5
+	call	putch
+	li	a5,0
+	mv	a0,a5
+	ld	ra,184(sp)
+	.cfi_restore 1
+	ld	s0,176(sp)
+	.cfi_restore 8
+	.cfi_def_cfa 2, 192
+	addi	sp,sp,192
+	.cfi_def_cfa_offset 0
+	jr	ra
+	.cfi_endproc
+.LFE1:
+	.size	main, .-main
+	.ident	"GCC: (GNU) 13.3.0"
+	.section	.note.GNU-stack,"",@progbits
diff --git a/quick_test/expect/asm2bin.toml b/quick_test/expect/asm2bin.toml
new file mode 100644
index 0000000..69a268c
--- /dev/null
+++ b/quick_test/expect/asm2bin.toml
@@ -0,0 +1,72 @@
+start_time = "2024-08-19 10:40:41.959101387 +08:00"
+end_time = "2024-08-19 10:40:42.231883071 +08:00"
+time_cost = "PT0.272781684S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/3.s"
+bin_path = "./sysy-data/quick_test/expect/bin/3"
+start_time = "2024-08-19 10:40:41.996936324 +08:00"
+end_time = "2024-08-19 10:40:42.039136575 +08:00"
+time_cost = "PT0.042200251S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/6.s"
+bin_path = "./sysy-data/quick_test/expect/bin/6"
+start_time = "2024-08-19 10:40:42.115555121 +08:00"
+end_time = "2024-08-19 10:40:42.154711390 +08:00"
+time_cost = "PT0.039156269S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/7.s"
+bin_path = "./sysy-data/quick_test/expect/bin/7"
+start_time = "2024-08-19 10:40:42.078437068 +08:00"
+end_time = "2024-08-19 10:40:42.114346725 +08:00"
+time_cost = "PT0.035909657S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/96_matrix_add.s"
+bin_path = "./sysy-data/quick_test/expect/bin/96_matrix_add"
+start_time = "2024-08-19 10:40:42.040208875 +08:00"
+end_time = "2024-08-19 10:40:42.077342720 +08:00"
+time_cost = "PT0.037133845S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/97_matrix_sub.s"
+bin_path = "./sysy-data/quick_test/expect/bin/97_matrix_sub"
+start_time = "2024-08-19 10:40:42.155871996 +08:00"
+end_time = "2024-08-19 10:40:42.192251180 +08:00"
+time_cost = "PT0.036379184S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/98_matrix_mul.s"
+bin_path = "./sysy-data/quick_test/expect/bin/98_matrix_mul"
+start_time = "2024-08-19 10:40:41.960070976 +08:00"
+end_time = "2024-08-19 10:40:41.995800509 +08:00"
+time_cost = "PT0.035729533S"
+success = true
+per_timeout = false
+
+[[asm2bin_asm]]
+asm_path = "./sysy-data/quick_test/expect/asm/99_matrix_tran.s"
+bin_path = "./sysy-data/quick_test/expect/bin/99_matrix_tran"
+start_time = "2024-08-19 10:40:42.193347329 +08:00"
+end_time = "2024-08-19 10:40:42.231805441 +08:00"
+time_cost = "PT0.038458112S"
+success = true
+per_timeout = false
diff --git a/quick_test/expect/bin/3 b/quick_test/expect/bin/3
new file mode 100755
index 0000000..e82524f
Binary files /dev/null and b/quick_test/expect/bin/3 differ
diff --git a/quick_test/expect/bin/6 b/quick_test/expect/bin/6
new file mode 100755
index 0000000..3b19685
Binary files /dev/null and b/quick_test/expect/bin/6 differ
diff --git a/quick_test/expect/bin/7 b/quick_test/expect/bin/7
new file mode 100755
index 0000000..6c2c667
Binary files /dev/null and b/quick_test/expect/bin/7 differ
diff --git a/quick_test/expect/bin/96_matrix_add b/quick_test/expect/bin/96_matrix_add
new file mode 100755
index 0000000..34187c1
Binary files /dev/null and b/quick_test/expect/bin/96_matrix_add differ
diff --git a/quick_test/expect/bin/97_matrix_sub b/quick_test/expect/bin/97_matrix_sub
new file mode 100755
index 0000000..0f33107
Binary files /dev/null and b/quick_test/expect/bin/97_matrix_sub differ
diff --git a/quick_test/expect/bin/98_matrix_mul b/quick_test/expect/bin/98_matrix_mul
new file mode 100755
index 0000000..b7084cb
Binary files /dev/null and b/quick_test/expect/bin/98_matrix_mul differ
diff --git a/quick_test/expect/bin/99_matrix_tran b/quick_test/expect/bin/99_matrix_tran
new file mode 100755
index 0000000..9654060
Binary files /dev/null and b/quick_test/expect/bin/99_matrix_tran differ
diff --git a/quick_test/expect/compile.toml b/quick_test/expect/compile.toml
new file mode 100644
index 0000000..b28fd62
--- /dev/null
+++ b/quick_test/expect/compile.toml
@@ -0,0 +1,72 @@
+start_time = "2024-08-19 10:40:41.789470145 +08:00"
+end_time = "2024-08-19 10:40:41.956642093 +08:00"
+time_cost = "PT0.167171948S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/3.sy"
+asm = "./sysy-data/quick_test/expect/asm/3.s"
+start_time = "2024-08-19 10:40:41.881476368 +08:00"
+end_time = "2024-08-19 10:40:41.906471431 +08:00"
+time_cost = "PT0.024995063S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/6.sy"
+asm = "./sysy-data/quick_test/expect/asm/6.s"
+start_time = "2024-08-19 10:40:41.848049371 +08:00"
+end_time = "2024-08-19 10:40:41.879859649 +08:00"
+time_cost = "PT0.031810278S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/7.sy"
+asm = "./sysy-data/quick_test/expect/asm/7.s"
+start_time = "2024-08-19 10:40:41.907593006 +08:00"
+end_time = "2024-08-19 10:40:41.938505146 +08:00"
+time_cost = "PT0.03091214S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/96_matrix_add.sy"
+asm = "./sysy-data/quick_test/expect/asm/96_matrix_add.s"
+start_time = "2024-08-19 10:40:41.828553042 +08:00"
+end_time = "2024-08-19 10:40:41.847141164 +08:00"
+time_cost = "PT0.018588122S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/97_matrix_sub.sy"
+asm = "./sysy-data/quick_test/expect/asm/97_matrix_sub.s"
+start_time = "2024-08-19 10:40:41.790579105 +08:00"
+end_time = "2024-08-19 10:40:41.808370739 +08:00"
+time_cost = "PT0.017791634S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/98_matrix_mul.sy"
+asm = "./sysy-data/quick_test/expect/asm/98_matrix_mul.s"
+start_time = "2024-08-19 10:40:41.939650490 +08:00"
+end_time = "2024-08-19 10:40:41.956567399 +08:00"
+time_cost = "PT0.016916909S"
+success = true
+per_timeout = false
+
+[[compile_sy]]
+sy = "./sysy-data/quick_test/sy/99_matrix_tran.sy"
+asm = "./sysy-data/quick_test/expect/asm/99_matrix_tran.s"
+start_time = "2024-08-19 10:40:41.809391051 +08:00"
+end_time = "2024-08-19 10:40:41.827769965 +08:00"
+time_cost = "PT0.018378914S"
+success = true
+per_timeout = false
diff --git a/quick_test/expect/execute.toml b/quick_test/expect/execute.toml
new file mode 100644
index 0000000..d5b41fa
--- /dev/null
+++ b/quick_test/expect/execute.toml
@@ -0,0 +1,79 @@
+start_time = "2024-08-19 10:40:42.233943665 +08:00"
+end_time = "2024-08-19 10:40:42.381256409 +08:00"
+time_cost = "PT0.147312744S"
+all_success = true
+success_num = 7
+failed_num = 0
+total_num = 7
+per_timeout_num = 0
+case_timeout = false
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/3"
+input_path = "./sysy-data/quick_test/input/3.in"
+output_path = "./sysy-data/quick_test/expect/output/3.out"
+start_time = "2024-08-19 10:40:42.365521373 +08:00"
+end_time = "2024-08-19 10:40:42.381131749 +08:00"
+time_cost = "PT0.015610376S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/6"
+input_path = "./sysy-data/quick_test/input/6.in"
+output_path = "./sysy-data/quick_test/expect/output/6.out"
+start_time = "2024-08-19 10:40:42.277847781 +08:00"
+end_time = "2024-08-19 10:40:42.298414266 +08:00"
+time_cost = "PT0.020566485S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/7"
+input_path = "./sysy-data/quick_test/input/7.in"
+output_path = "./sysy-data/quick_test/expect/output/7.out"
+start_time = "2024-08-19 10:40:42.324830814 +08:00"
+end_time = "2024-08-19 10:40:42.346191709 +08:00"
+time_cost = "PT0.021360895S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/96_matrix_add"
+input_path = "./sysy-data/quick_test/input/96_matrix_add.in"
+output_path = "./sysy-data/quick_test/expect/output/96_matrix_add.out"
+start_time = "2024-08-19 10:40:42.235238892 +08:00"
+end_time = "2024-08-19 10:40:42.255301634 +08:00"
+time_cost = "PT0.020062742S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/97_matrix_sub"
+input_path = "./sysy-data/quick_test/input/97_matrix_sub.in"
+output_path = "./sysy-data/quick_test/expect/output/97_matrix_sub.out"
+start_time = "2024-08-19 10:40:42.347704022 +08:00"
+end_time = "2024-08-19 10:40:42.364089989 +08:00"
+time_cost = "PT0.016385967S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/98_matrix_mul"
+input_path = "./sysy-data/quick_test/input/98_matrix_mul.in"
+output_path = "./sysy-data/quick_test/expect/output/98_matrix_mul.out"
+start_time = "2024-08-19 10:40:42.256932188 +08:00"
+end_time = "2024-08-19 10:40:42.276185888 +08:00"
+time_cost = "PT0.0192537S"
+per_timeout = false
+success = true
+
+[[execute_bin]]
+bin_path = "./sysy-data/quick_test/expect/bin/99_matrix_tran"
+input_path = "./sysy-data/quick_test/input/99_matrix_tran.in"
+output_path = "./sysy-data/quick_test/expect/output/99_matrix_tran.out"
+start_time = "2024-08-19 10:40:42.299621770 +08:00"
+end_time = "2024-08-19 10:40:42.323521978 +08:00"
+time_cost = "PT0.023900208S"
+per_timeout = false
+success = true
diff --git a/quick_test/expect/log/3.log b/quick_test/expect/log/3.log
new file mode 100644
index 0000000..2c3b946
--- /dev/null
+++ b/quick_test/expect/log/3.log
@@ -0,0 +1,63 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/6.log b/quick_test/expect/log/6.log
new file mode 100644
index 0000000..2a7d133
--- /dev/null
+++ b/quick_test/expect/log/6.log
@@ -0,0 +1,61 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/7.log b/quick_test/expect/log/7.log
new file mode 100644
index 0000000..7a56675
--- /dev/null
+++ b/quick_test/expect/log/7.log
@@ -0,0 +1,69 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+./sysy-data/quick_test/sy/7.sy: In function 'main':
+./sysy-data/quick_test/sy/7.sy:11:9: error: redefinition of 'n'
+   11 |     int n = thrd_create(4);
+      |         ^
+./sysy-data/quick_test/sy/7.sy:7:9: note: previous definition of 'n' with type 'int'
+    7 |     int n = thrd_create(4);
+      |         ^
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+./sysy-data/quick_test/sy/7.sy: In function 'main':
+./sysy-data/quick_test/sy/7.sy:11:9: error: redefinition of 'n'
+   11 |     int n = thrd_create(4);
+      |         ^
+./sysy-data/quick_test/sy/7.sy:7:9: note: previous definition of 'n' with type 'int'
+    7 |     int n = thrd_create(4);
+      |         ^
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/96_matrix_add.log b/quick_test/expect/log/96_matrix_add.log
new file mode 100644
index 0000000..c40ebb0
--- /dev/null
+++ b/quick_test/expect/log/96_matrix_add.log
@@ -0,0 +1,36 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/97_matrix_sub.log b/quick_test/expect/log/97_matrix_sub.log
new file mode 100644
index 0000000..c40ebb0
--- /dev/null
+++ b/quick_test/expect/log/97_matrix_sub.log
@@ -0,0 +1,36 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/98_matrix_mul.log b/quick_test/expect/log/98_matrix_mul.log
new file mode 100644
index 0000000..c40ebb0
--- /dev/null
+++ b/quick_test/expect/log/98_matrix_mul.log
@@ -0,0 +1,36 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/log/99_matrix_tran.log b/quick_test/expect/log/99_matrix_tran.log
new file mode 100644
index 0000000..c40ebb0
--- /dev/null
+++ b/quick_test/expect/log/99_matrix_tran.log
@@ -0,0 +1,36 @@
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
+stdout:
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/expect/output/3.out b/quick_test/expect/output/3.out
new file mode 100644
index 0000000..f05272c
--- /dev/null
+++ b/quick_test/expect/output/3.out
@@ -0,0 +1,3 @@
+8: 0 0 0 0 0 0 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/6.out b/quick_test/expect/output/6.out
new file mode 100644
index 0000000..aba0265
--- /dev/null
+++ b/quick_test/expect/output/6.out
@@ -0,0 +1,3 @@
+8: 22 2 8 10 2 4 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/7.out b/quick_test/expect/output/7.out
new file mode 100644
index 0000000..1be4e05
--- /dev/null
+++ b/quick_test/expect/output/7.out
@@ -0,0 +1,4 @@
+8: 2 2 8 10 2 4 0 0
+8: 4 4 16 20 4 4 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/96_matrix_add.out b/quick_test/expect/output/96_matrix_add.out
new file mode 100644
index 0000000..7c9f979
--- /dev/null
+++ b/quick_test/expect/output/96_matrix_add.out
@@ -0,0 +1,5 @@
+024
+024
+024
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/97_matrix_sub.out b/quick_test/expect/output/97_matrix_sub.out
new file mode 100644
index 0000000..9e10637
--- /dev/null
+++ b/quick_test/expect/output/97_matrix_sub.out
@@ -0,0 +1,5 @@
+000
+000
+000
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/98_matrix_mul.out b/quick_test/expect/output/98_matrix_mul.out
new file mode 100644
index 0000000..7b66a70
--- /dev/null
+++ b/quick_test/expect/output/98_matrix_mul.out
@@ -0,0 +1,5 @@
+036
+036
+036
+
+0
\ No newline at end of file
diff --git a/quick_test/expect/output/99_matrix_tran.out b/quick_test/expect/output/99_matrix_tran.out
new file mode 100644
index 0000000..dfc4f84
--- /dev/null
+++ b/quick_test/expect/output/99_matrix_tran.out
@@ -0,0 +1,5 @@
+000
+111
+222
+
+0
\ No newline at end of file
diff --git a/quick_test/ll/3.ll b/quick_test/ll/3.ll
new file mode 100644
index 0000000..d0e3d80
--- /dev/null
+++ b/quick_test/ll/3.ll
@@ -0,0 +1,50 @@
+@A = dso_local global [9 x i32] zeroinitializer
+@B = dso_local global [9 x i32] zeroinitializer
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+entry:
+%getelementptr_7 = getelementptr [9 x i32], ptr @A, i32 0, i32 0
+%call_8 = call i32 @getarray(i32* %getelementptr_7)
+%call_31 = call i32 @thrd_create(i32 4)
+%Mul_33 = mul i32 %call_31, 8
+%SDiv_34 = sdiv i32 %Mul_33, 5
+%Add_36 = add i32 %Mul_33, 8
+%SDiv_37 = sdiv i32 %Add_36, 5
+br label %cond0
+
+cond0:
+%phi_30 = phi i32 [%SDiv_34, %entry], [%Add_14, %body1]
+%icmp_39 = icmp slt i32 %phi_30, %SDiv_37
+br i1 %icmp_39, label %body1, label %exit
+
+body1:
+%Add_14 = add i32 %phi_30, 1
+%getelementptr_17 = getelementptr [9 x i32], ptr @A, i32 0, i32 %Add_14
+%getelementptr_19 = getelementptr [9 x i32], ptr @B, i32 0, i32 %Add_14
+%load_20 = load i32, ptr %getelementptr_17
+store i32 %load_20, ptr %getelementptr_19
+br label %cond0
+
+exit:
+call void @thrd_join()
+%getelementptr_26 = getelementptr [9 x i32], ptr @B, i32 0, i32 0
+call void @putarray(i32 8, i32* %getelementptr_26)
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/6.ll b/quick_test/ll/6.ll
new file mode 100644
index 0000000..9b50059
--- /dev/null
+++ b/quick_test/ll/6.ll
@@ -0,0 +1,32 @@
+@A = dso_local global [9 x i32] [i32 1, i32 1, i32 4, i32 5, i32 1, i32 4, i32 0, i32 0, i32 0]
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+exit:
+%getelementptr_5 = getelementptr [9 x i32], ptr @A, i32 0, i32 0
+store i32 11, ptr %getelementptr_5
+%call_8 = call i32 @thrd_create(i32 4)
+%getelementptr_11 = getelementptr [9 x i32], ptr @A, i32 0, i32 %call_8
+%load_12 = load i32, ptr %getelementptr_11
+%Mul_13 = mul i32 %load_12, 2
+store i32 %Mul_13, ptr %getelementptr_11
+call void @thrd_join()
+call void @putarray(i32 8, i32* %getelementptr_5)
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/7.ll b/quick_test/ll/7.ll
new file mode 100644
index 0000000..392ebce
--- /dev/null
+++ b/quick_test/ll/7.ll
@@ -0,0 +1,38 @@
+@A = dso_local global [9 x i32] [i32 1, i32 1, i32 4, i32 5, i32 1, i32 4, i32 0, i32 0, i32 0]
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+exit:
+%call_6 = call i32 @thrd_create(i32 4)
+%getelementptr_9 = getelementptr [9 x i32], ptr @A, i32 0, i32 %call_6
+%load_10 = load i32, ptr %getelementptr_9
+%Mul_11 = mul i32 %load_10, 2
+store i32 %Mul_11, ptr %getelementptr_9
+call void @thrd_join()
+%getelementptr_16 = getelementptr [9 x i32], ptr @A, i32 0, i32 0
+call void @putarray(i32 8, i32* %getelementptr_16)
+%call_19 = call i32 @thrd_create(i32 4)
+%getelementptr_22 = getelementptr [9 x i32], ptr @A, i32 0, i32 %call_19
+%load_23 = load i32, ptr %getelementptr_22
+%Mul_24 = mul i32 %load_23, 2
+store i32 %Mul_24, ptr %getelementptr_22
+call void @thrd_join()
+call void @putarray(i32 8, i32* %getelementptr_16)
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/96_matrix_add.ll b/quick_test/ll/96_matrix_add.ll
new file mode 100644
index 0000000..05cfe19
--- /dev/null
+++ b/quick_test/ll/96_matrix_add.ll
@@ -0,0 +1,111 @@
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+@N = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @add(float* %a0, float* %a1, float* %a2, float* %b0, float* %b1, float* %b2, float* %c0, float* %c1, float* %c2) {
+entry:
+br label %cond0
+
+cond0:
+%phi_141 = phi i32 [0, %entry], [%Add_69, %body1]
+%load_73 = load i32, ptr @M
+%icmp_74 = icmp slt i32 %phi_141, %load_73
+br i1 %icmp_74, label %body1, label %exit
+
+body1:
+%getelementptr_31 = getelementptr float, ptr %a0, i32 %phi_141
+%getelementptr_34 = getelementptr float, ptr %b0, i32 %phi_141
+%load_35 = load float, ptr %getelementptr_31
+%load_36 = load float, ptr %getelementptr_34
+%FAdd_37 = fadd float %load_35, %load_36
+%getelementptr_40 = getelementptr float, ptr %c0, i32 %phi_141
+store float %FAdd_37, ptr %getelementptr_40
+%getelementptr_44 = getelementptr float, ptr %a1, i32 %phi_141
+%getelementptr_47 = getelementptr float, ptr %b1, i32 %phi_141
+%load_48 = load float, ptr %getelementptr_44
+%load_49 = load float, ptr %getelementptr_47
+%FAdd_50 = fadd float %load_48, %load_49
+%getelementptr_53 = getelementptr float, ptr %c1, i32 %phi_141
+store float %FAdd_50, ptr %getelementptr_53
+%getelementptr_57 = getelementptr float, ptr %a2, i32 %phi_141
+%getelementptr_60 = getelementptr float, ptr %b2, i32 %phi_141
+%load_61 = load float, ptr %getelementptr_57
+%load_62 = load float, ptr %getelementptr_60
+%FAdd_63 = fadd float %load_61, %load_62
+%getelementptr_66 = getelementptr float, ptr %c2, i32 %phi_141
+store float %FAdd_63, ptr %getelementptr_66
+%Add_69 = add i32 %phi_141, 1
+br label %cond0
+
+exit:
+ret i32 0
+
+
+}
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_86 = alloca [3 x float]
+%alloca_87 = alloca [3 x float]
+%alloca_88 = alloca [3 x float]
+%alloca_89 = alloca [3 x float]
+%alloca_90 = alloca [3 x float]
+%alloca_91 = alloca [3 x float]
+%getelementptr_143 = getelementptr [3 x float], ptr %alloca_88, i32 0
+%getelementptr_144 = getelementptr [3 x float], ptr %alloca_91, i32 0
+%getelementptr_145 = getelementptr [3 x float], ptr %alloca_89, i32 0
+%getelementptr_146 = getelementptr [3 x float], ptr %alloca_86, i32 0
+%getelementptr_147 = getelementptr [3 x float], ptr %alloca_90, i32 0
+%getelementptr_148 = getelementptr [3 x float], ptr %alloca_87, i32 0
+%call_149 = call i32 @thrd_create(i32 4)
+%Mul_151 = mul i32 %call_149, 3
+%SDiv_152 = sdiv i32 %Mul_151, 5
+%Add_154 = add i32 %Mul_151, 3
+%SDiv_155 = sdiv i32 %Add_154, 5
+br label %cond0
+
+cond0:
+%phi_142 = phi i32 [%SDiv_152, %entry], [%Add_132, %body1]
+%icmp_157 = icmp slt i32 %phi_142, %SDiv_155
+br i1 %icmp_157, label %body1, label %exit
+
+body1:
+%getelementptr_102 = getelementptr [3 x float], ptr %getelementptr_146, i32 0, i32 %phi_142
+%itofp_104 = sitofp i32 %phi_142 to float
+store float %itofp_104, ptr %getelementptr_102
+%getelementptr_107 = getelementptr [3 x float], ptr %getelementptr_148, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_107
+%getelementptr_112 = getelementptr [3 x float], ptr %getelementptr_143, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_112
+%getelementptr_117 = getelementptr [3 x float], ptr %getelementptr_145, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_117
+%getelementptr_122 = getelementptr [3 x float], ptr %getelementptr_147, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_122
+%getelementptr_127 = getelementptr [3 x float], ptr %getelementptr_144, i32 0, i32 %phi_142
+store float %itofp_104, ptr %getelementptr_127
+%Add_132 = add i32 %phi_142, 1
+br label %cond0
+
+exit:
+call void @thrd_join()
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/97_matrix_sub.ll b/quick_test/ll/97_matrix_sub.ll
new file mode 100644
index 0000000..477904c
--- /dev/null
+++ b/quick_test/ll/97_matrix_sub.ll
@@ -0,0 +1,194 @@
+@N = dso_local global i32 0
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_85 = alloca [3 x float]
+%alloca_86 = alloca [3 x float]
+%alloca_87 = alloca [3 x float]
+%alloca_88 = alloca [3 x float]
+%alloca_89 = alloca [3 x float]
+%alloca_90 = alloca [3 x float]
+%alloca_91 = alloca [6 x float]
+%alloca_92 = alloca [3 x float]
+%alloca_93 = alloca [3 x float]
+%getelementptr_281 = getelementptr [3 x float], ptr %alloca_90, i32 0
+%getelementptr_282 = getelementptr [3 x float], ptr %alloca_88, i32 0
+%getelementptr_283 = getelementptr [3 x float], ptr %alloca_85, i32 0
+%getelementptr_284 = getelementptr [3 x float], ptr %alloca_87, i32 0
+%getelementptr_285 = getelementptr [3 x float], ptr %alloca_89, i32 0
+%getelementptr_286 = getelementptr [3 x float], ptr %alloca_86, i32 0
+%call_287 = call i32 @thrd_create(i32 4)
+%Mul_289 = mul i32 %call_287, 3
+%SDiv_290 = sdiv i32 %Mul_289, 5
+%Add_292 = add i32 %Mul_289, 3
+%SDiv_293 = sdiv i32 %Add_292, 5
+br label %cond0
+
+cond0:
+%phi_217 = phi i32 [%SDiv_290, %entry], [%Add_131, %body1]
+%icmp_295 = icmp slt i32 %phi_217, %SDiv_293
+br i1 %icmp_295, label %body1, label %entry_inline0
+
+body1:
+%getelementptr_101 = getelementptr [3 x float], ptr %getelementptr_283, i32 0, i32 %phi_217
+%itofp_103 = sitofp i32 %phi_217 to float
+store float %itofp_103, ptr %getelementptr_101
+%getelementptr_106 = getelementptr [3 x float], ptr %getelementptr_286, i32 0, i32 %phi_217
+store float %itofp_103, ptr %getelementptr_106
+%getelementptr_111 = getelementptr [3 x float], ptr %getelementptr_284, i32 0, i32 %phi_217
+store float %itofp_103, ptr %getelementptr_111
+%getelementptr_116 = getelementptr [3 x float], ptr %getelementptr_282, i32 0, i32 %phi_217
+store float %itofp_103, ptr %getelementptr_116
+%getelementptr_121 = getelementptr [3 x float], ptr %getelementptr_285, i32 0, i32 %phi_217
+store float %itofp_103, ptr %getelementptr_121
+%getelementptr_126 = getelementptr [3 x float], ptr %getelementptr_281, i32 0, i32 %phi_217
+store float %itofp_103, ptr %getelementptr_126
+%Add_131 = add i32 %phi_217, 1
+br label %cond0
+
+entry_inline0:
+call void @thrd_join()
+%getelementptr_297 = getelementptr [3 x float], ptr %alloca_86, i32 0
+%getelementptr_298 = getelementptr [3 x float], ptr %alloca_90, i32 0
+%getelementptr_299 = getelementptr [3 x float], ptr %alloca_88, i32 0
+%getelementptr_300 = getelementptr [3 x float], ptr %alloca_93, i32 0
+%getelementptr_301 = getelementptr [3 x float], ptr %alloca_92, i32 0
+%getelementptr_302 = getelementptr [3 x float], ptr %alloca_89, i32 0
+%getelementptr_303 = getelementptr [3 x float], ptr %alloca_85, i32 0
+%getelementptr_304 = getelementptr [3 x float], ptr %alloca_87, i32 0
+%getelementptr_305 = getelementptr [6 x float], ptr %alloca_91, i32 0
+%call_306 = call i32 @thrd_create(i32 4)
+%Mul_308 = mul i32 %call_306, 3
+%SDiv_309 = sdiv i32 %Mul_308, 5
+%Add_311 = add i32 %Mul_308, 3
+%SDiv_312 = sdiv i32 %Add_311, 5
+br label %cond0_inline1
+
+cond0_inline1:
+%phi_238 = phi i32 [%SDiv_309, %entry_inline0], [%Add_267, %body1_inline4]
+%icmp_314 = icmp slt i32 %phi_238, %SDiv_312
+br i1 %icmp_314, label %body1_inline4, label %final2_split5
+
+body1_inline4:
+%getelementptr_272 = getelementptr [3 x float], ptr %getelementptr_303, i32 0, i32 %phi_238
+%getelementptr_273 = getelementptr [3 x float], ptr %getelementptr_299, i32 0, i32 %phi_238
+%load_248 = load float, ptr %getelementptr_272
+%load_249 = load float, ptr %getelementptr_273
+%FSub_250 = fsub float %load_248, %load_249
+%getelementptr_274 = getelementptr [6 x float], ptr %getelementptr_305, i32 0, i32 %phi_238
+store float %FSub_250, ptr %getelementptr_274
+%getelementptr_275 = getelementptr [3 x float], ptr %getelementptr_297, i32 0, i32 %phi_238
+%getelementptr_276 = getelementptr [3 x float], ptr %getelementptr_302, i32 0, i32 %phi_238
+%load_255 = load float, ptr %getelementptr_275
+%load_256 = load float, ptr %getelementptr_276
+%FSub_257 = fsub float %load_255, %load_256
+%getelementptr_277 = getelementptr [3 x float], ptr %getelementptr_301, i32 0, i32 %phi_238
+store float %FSub_257, ptr %getelementptr_277
+%getelementptr_278 = getelementptr [3 x float], ptr %getelementptr_304, i32 0, i32 %phi_238
+%getelementptr_279 = getelementptr [3 x float], ptr %getelementptr_298, i32 0, i32 %phi_238
+%load_262 = load float, ptr %getelementptr_278
+%load_263 = load float, ptr %getelementptr_279
+%FSub_264 = fsub float %load_262, %load_263
+%getelementptr_280 = getelementptr [3 x float], ptr %getelementptr_300, i32 0, i32 %phi_238
+store float %FSub_264, ptr %getelementptr_280
+%Add_267 = add i32 %phi_238, 1
+br label %cond0_inline1
+
+final2_split5:
+call void @thrd_join()
+%getelementptr_316 = getelementptr [6 x float], ptr %alloca_91, i32 0
+%call_317 = call i32 @thrd_create(i32 4)
+%Mul_319 = mul i32 %call_317, 3
+%SDiv_320 = sdiv i32 %Mul_319, 5
+%Add_322 = add i32 %Mul_319, 3
+%SDiv_323 = sdiv i32 %Add_322, 5
+br label %cond3
+
+cond3:
+%phi_218 = phi i32 [%SDiv_320, %final2_split5], [%Add_161, %body4]
+%icmp_325 = icmp slt i32 %phi_218, %SDiv_323
+br i1 %icmp_325, label %body4, label %final5
+
+body4:
+%getelementptr_154 = getelementptr [6 x float], ptr %getelementptr_316, i32 0, i32 %phi_218
+%load_155 = load float, ptr %getelementptr_154
+%fptoi_156 = fptosi float %load_155 to i32
+call void @putint(i32 %fptoi_156)
+%Add_161 = add i32 %phi_218, 1
+br label %cond3
+
+final5:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_327 = getelementptr [3 x float], ptr %alloca_92, i32 0
+%call_328 = call i32 @thrd_create(i32 4)
+%Mul_330 = mul i32 %call_328, 3
+%SDiv_331 = sdiv i32 %Mul_330, 5
+%Add_333 = add i32 %Mul_330, 3
+%SDiv_334 = sdiv i32 %Add_333, 5
+br label %cond6
+
+cond6:
+%phi_219 = phi i32 [%SDiv_331, %final5], [%Add_183, %body7]
+%icmp_336 = icmp slt i32 %phi_219, %SDiv_334
+br i1 %icmp_336, label %body7, label %final8
+
+body7:
+%getelementptr_176 = getelementptr [3 x float], ptr %getelementptr_327, i32 0, i32 %phi_219
+%load_177 = load float, ptr %getelementptr_176
+%fptoi_178 = fptosi float %load_177 to i32
+call void @putint(i32 %fptoi_178)
+%Add_183 = add i32 %phi_219, 1
+br label %cond6
+
+final8:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_338 = getelementptr [3 x float], ptr %alloca_93, i32 0
+%call_339 = call i32 @thrd_create(i32 4)
+%Mul_341 = mul i32 %call_339, 3
+%SDiv_342 = sdiv i32 %Mul_341, 5
+%Add_344 = add i32 %Mul_341, 3
+%SDiv_345 = sdiv i32 %Add_344, 5
+br label %cond9
+
+cond9:
+%phi_220 = phi i32 [%SDiv_342, %final8], [%Add_205, %body10]
+%icmp_347 = icmp slt i32 %phi_220, %SDiv_345
+br i1 %icmp_347, label %body10, label %exit
+
+body10:
+%getelementptr_198 = getelementptr [3 x float], ptr %getelementptr_338, i32 0, i32 %phi_220
+%load_199 = load float, ptr %getelementptr_198
+%fptoi_200 = fptosi float %load_199 to i32
+call void @putint(i32 %fptoi_200)
+%Add_205 = add i32 %phi_220, 1
+br label %cond9
+
+exit:
+call void @thrd_join()
+call void @putch(i32 10)
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/98_matrix_mul.ll b/quick_test/ll/98_matrix_mul.ll
new file mode 100644
index 0000000..fa0364c
--- /dev/null
+++ b/quick_test/ll/98_matrix_mul.ll
@@ -0,0 +1,245 @@
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+@N = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_269 = alloca [3 x float]
+%alloca_270 = alloca [3 x float]
+%alloca_271 = alloca [3 x float]
+%alloca_272 = alloca [3 x float]
+%alloca_273 = alloca [3 x float]
+%alloca_274 = alloca [3 x float]
+%alloca_275 = alloca [6 x float]
+%alloca_276 = alloca [3 x float]
+%alloca_277 = alloca [3 x float]
+%getelementptr_663 = getelementptr [3 x float], ptr %alloca_269, i32 0
+%getelementptr_664 = getelementptr [3 x float], ptr %alloca_271, i32 0
+%getelementptr_665 = getelementptr [3 x float], ptr %alloca_274, i32 0
+%getelementptr_666 = getelementptr [3 x float], ptr %alloca_273, i32 0
+%getelementptr_667 = getelementptr [3 x float], ptr %alloca_272, i32 0
+%getelementptr_668 = getelementptr [3 x float], ptr %alloca_270, i32 0
+%call_669 = call i32 @thrd_create(i32 4)
+%Mul_671 = mul i32 %call_669, 3
+%SDiv_672 = sdiv i32 %Mul_671, 5
+%Add_674 = add i32 %Mul_671, 3
+%SDiv_675 = sdiv i32 %Add_674, 5
+br label %cond0
+
+cond0:
+%phi_404 = phi i32 [%SDiv_672, %entry], [%Add_315, %body1]
+%icmp_677 = icmp slt i32 %phi_404, %SDiv_675
+br i1 %icmp_677, label %body1, label %final2_split2
+
+body1:
+%getelementptr_285 = getelementptr [3 x float], ptr %getelementptr_663, i32 0, i32 %phi_404
+%itofp_287 = sitofp i32 %phi_404 to float
+store float %itofp_287, ptr %getelementptr_285
+%getelementptr_290 = getelementptr [3 x float], ptr %getelementptr_668, i32 0, i32 %phi_404
+store float %itofp_287, ptr %getelementptr_290
+%getelementptr_295 = getelementptr [3 x float], ptr %getelementptr_664, i32 0, i32 %phi_404
+store float %itofp_287, ptr %getelementptr_295
+%getelementptr_300 = getelementptr [3 x float], ptr %getelementptr_667, i32 0, i32 %phi_404
+store float %itofp_287, ptr %getelementptr_300
+%getelementptr_305 = getelementptr [3 x float], ptr %getelementptr_666, i32 0, i32 %phi_404
+store float %itofp_287, ptr %getelementptr_305
+%getelementptr_310 = getelementptr [3 x float], ptr %getelementptr_665, i32 0, i32 %phi_404
+store float %itofp_287, ptr %getelementptr_310
+%Add_315 = add i32 %phi_404, 1
+br label %cond0
+
+final2_split2:
+call void @thrd_join()
+%getelementptr_600 = getelementptr [3 x float], ptr %alloca_269, i32 0, i32 0
+%getelementptr_601 = getelementptr [3 x float], ptr %alloca_272, i32 0, i32 0
+%load_425 = load float, ptr %getelementptr_600
+%load_426 = load float, ptr %getelementptr_601
+%FMul_427 = fmul float %load_425, %load_426
+%getelementptr_602 = getelementptr [3 x float], ptr %alloca_269, i32 0, i32 1
+%getelementptr_603 = getelementptr [3 x float], ptr %alloca_273, i32 0, i32 0
+%load_430 = load float, ptr %getelementptr_602
+%load_431 = load float, ptr %getelementptr_603
+%FMul_432 = fmul float %load_430, %load_431
+%FAdd_433 = fadd float %FMul_427, %FMul_432
+%getelementptr_604 = getelementptr [3 x float], ptr %alloca_269, i32 0, i32 2
+%getelementptr_605 = getelementptr [3 x float], ptr %alloca_274, i32 0, i32 0
+%load_436 = load float, ptr %getelementptr_604
+%load_437 = load float, ptr %getelementptr_605
+%FMul_438 = fmul float %load_436, %load_437
+%FAdd_439 = fadd float %FAdd_433, %FMul_438
+%getelementptr_606 = getelementptr [6 x float], ptr %alloca_275, i32 0, i32 0
+store float %FAdd_439, ptr %getelementptr_606
+%getelementptr_608 = getelementptr [3 x float], ptr %alloca_272, i32 0, i32 1
+%load_445 = load float, ptr %getelementptr_608
+%FMul_446 = fmul float %load_425, %load_445
+%getelementptr_610 = getelementptr [3 x float], ptr %alloca_273, i32 0, i32 1
+%load_450 = load float, ptr %getelementptr_610
+%FMul_451 = fmul float %load_430, %load_450
+%FAdd_452 = fadd float %FMul_446, %FMul_451
+%getelementptr_612 = getelementptr [3 x float], ptr %alloca_274, i32 0, i32 1
+%load_456 = load float, ptr %getelementptr_612
+%FMul_457 = fmul float %load_436, %load_456
+%FAdd_458 = fadd float %FAdd_452, %FMul_457
+%getelementptr_613 = getelementptr [6 x float], ptr %alloca_275, i32 0, i32 1
+store float %FAdd_458, ptr %getelementptr_613
+%getelementptr_615 = getelementptr [3 x float], ptr %alloca_272, i32 0, i32 2
+%load_464 = load float, ptr %getelementptr_615
+%FMul_465 = fmul float %load_425, %load_464
+%getelementptr_617 = getelementptr [3 x float], ptr %alloca_273, i32 0, i32 2
+%load_469 = load float, ptr %getelementptr_617
+%FMul_470 = fmul float %load_430, %load_469
+%FAdd_471 = fadd float %FMul_465, %FMul_470
+%getelementptr_619 = getelementptr [3 x float], ptr %alloca_274, i32 0, i32 2
+%load_475 = load float, ptr %getelementptr_619
+%FMul_476 = fmul float %load_436, %load_475
+%FAdd_477 = fadd float %FAdd_471, %FMul_476
+%getelementptr_620 = getelementptr [6 x float], ptr %alloca_275, i32 0, i32 2
+store float %FAdd_477, ptr %getelementptr_620
+%getelementptr_621 = getelementptr [3 x float], ptr %alloca_270, i32 0, i32 0
+%load_482 = load float, ptr %getelementptr_621
+%FMul_484 = fmul float %load_482, %load_426
+%getelementptr_623 = getelementptr [3 x float], ptr %alloca_270, i32 0, i32 1
+%load_487 = load float, ptr %getelementptr_623
+%FMul_489 = fmul float %load_487, %load_431
+%FAdd_490 = fadd float %FMul_484, %FMul_489
+%getelementptr_625 = getelementptr [3 x float], ptr %alloca_270, i32 0, i32 2
+%load_493 = load float, ptr %getelementptr_625
+%FMul_495 = fmul float %load_493, %load_437
+%FAdd_496 = fadd float %FAdd_490, %FMul_495
+%getelementptr_627 = getelementptr [3 x float], ptr %alloca_276, i32 0, i32 0
+store float %FAdd_496, ptr %getelementptr_627
+%FMul_503 = fmul float %load_482, %load_445
+%FMul_508 = fmul float %load_487, %load_450
+%FAdd_509 = fadd float %FMul_503, %FMul_508
+%FMul_514 = fmul float %load_493, %load_456
+%FAdd_515 = fadd float %FAdd_509, %FMul_514
+%getelementptr_634 = getelementptr [3 x float], ptr %alloca_276, i32 0, i32 1
+store float %FAdd_515, ptr %getelementptr_634
+%FMul_522 = fmul float %load_482, %load_464
+%FMul_527 = fmul float %load_487, %load_469
+%FAdd_528 = fadd float %FMul_522, %FMul_527
+%FMul_533 = fmul float %load_493, %load_475
+%FAdd_534 = fadd float %FAdd_528, %FMul_533
+%getelementptr_641 = getelementptr [3 x float], ptr %alloca_276, i32 0, i32 2
+store float %FAdd_534, ptr %getelementptr_641
+%getelementptr_642 = getelementptr [3 x float], ptr %alloca_271, i32 0, i32 0
+%load_539 = load float, ptr %getelementptr_642
+%FMul_541 = fmul float %load_539, %load_426
+%getelementptr_644 = getelementptr [3 x float], ptr %alloca_271, i32 0, i32 1
+%load_544 = load float, ptr %getelementptr_644
+%FMul_546 = fmul float %load_544, %load_431
+%FAdd_547 = fadd float %FMul_541, %FMul_546
+%getelementptr_646 = getelementptr [3 x float], ptr %alloca_271, i32 0, i32 2
+%load_550 = load float, ptr %getelementptr_646
+%FMul_552 = fmul float %load_550, %load_437
+%FAdd_553 = fadd float %FAdd_547, %FMul_552
+%getelementptr_648 = getelementptr [3 x float], ptr %alloca_277, i32 0, i32 0
+store float %FAdd_553, ptr %getelementptr_648
+%FMul_560 = fmul float %load_539, %load_445
+%FMul_565 = fmul float %load_544, %load_450
+%FAdd_566 = fadd float %FMul_560, %FMul_565
+%FMul_571 = fmul float %load_550, %load_456
+%FAdd_572 = fadd float %FAdd_566, %FMul_571
+%getelementptr_655 = getelementptr [3 x float], ptr %alloca_277, i32 0, i32 1
+store float %FAdd_572, ptr %getelementptr_655
+%FMul_579 = fmul float %load_539, %load_464
+%FMul_584 = fmul float %load_544, %load_469
+%FAdd_585 = fadd float %FMul_579, %FMul_584
+%FMul_590 = fmul float %load_550, %load_475
+%FAdd_591 = fadd float %FAdd_585, %FMul_590
+%getelementptr_662 = getelementptr [3 x float], ptr %alloca_277, i32 0, i32 2
+store float %FAdd_591, ptr %getelementptr_662
+%getelementptr_679 = getelementptr [6 x float], ptr %alloca_275, i32 0
+%call_680 = call i32 @thrd_create(i32 4)
+%Mul_682 = mul i32 %call_680, 3
+%SDiv_683 = sdiv i32 %Mul_682, 5
+%Add_685 = add i32 %Mul_682, 3
+%SDiv_686 = sdiv i32 %Add_685, 5
+br label %cond3
+
+cond3:
+%phi_405 = phi i32 [%SDiv_683, %final2_split2], [%Add_346, %body4]
+%icmp_688 = icmp slt i32 %phi_405, %SDiv_686
+br i1 %icmp_688, label %body4, label %final5
+
+body4:
+%getelementptr_339 = getelementptr [6 x float], ptr %getelementptr_679, i32 0, i32 %phi_405
+%load_340 = load float, ptr %getelementptr_339
+%fptoi_341 = fptosi float %load_340 to i32
+call void @putint(i32 %fptoi_341)
+%Add_346 = add i32 %phi_405, 1
+br label %cond3
+
+final5:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_690 = getelementptr [3 x float], ptr %alloca_276, i32 0
+%call_691 = call i32 @thrd_create(i32 4)
+%Mul_693 = mul i32 %call_691, 3
+%SDiv_694 = sdiv i32 %Mul_693, 5
+%Add_696 = add i32 %Mul_693, 3
+%SDiv_697 = sdiv i32 %Add_696, 5
+br label %cond6
+
+cond6:
+%phi_406 = phi i32 [%SDiv_694, %final5], [%Add_369, %body7]
+%icmp_699 = icmp slt i32 %phi_406, %SDiv_697
+br i1 %icmp_699, label %body7, label %final8
+
+body7:
+%getelementptr_362 = getelementptr [3 x float], ptr %getelementptr_690, i32 0, i32 %phi_406
+%load_363 = load float, ptr %getelementptr_362
+%fptoi_364 = fptosi float %load_363 to i32
+call void @putint(i32 %fptoi_364)
+%Add_369 = add i32 %phi_406, 1
+br label %cond6
+
+final8:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_701 = getelementptr [3 x float], ptr %alloca_277, i32 0
+%call_702 = call i32 @thrd_create(i32 4)
+%Mul_704 = mul i32 %call_702, 3
+%SDiv_705 = sdiv i32 %Mul_704, 5
+%Add_707 = add i32 %Mul_704, 3
+%SDiv_708 = sdiv i32 %Add_707, 5
+br label %cond9
+
+cond9:
+%phi_407 = phi i32 [%SDiv_705, %final8], [%Add_392, %body10]
+%icmp_710 = icmp slt i32 %phi_407, %SDiv_708
+br i1 %icmp_710, label %body10, label %exit
+
+body10:
+%getelementptr_385 = getelementptr [3 x float], ptr %getelementptr_701, i32 0, i32 %phi_407
+%load_386 = load float, ptr %getelementptr_385
+%fptoi_387 = fptosi float %load_386 to i32
+call void @putint(i32 %fptoi_387)
+%Add_392 = add i32 %phi_407, 1
+br label %cond9
+
+exit:
+call void @thrd_join()
+call void @putch(i32 10)
+ret i32 0
+
+
+}
diff --git a/quick_test/ll/99_matrix_tran.ll b/quick_test/ll/99_matrix_tran.ll
new file mode 100644
index 0000000..a1dc399
--- /dev/null
+++ b/quick_test/ll/99_matrix_tran.ll
@@ -0,0 +1,182 @@
+@M = dso_local global i32 0
+@L = dso_local global i32 0
+@N = dso_local global i32 0
+declare i32 @getint()
+declare i32 @getch()
+declare float @getfloat()
+declare void @putint(i32 %p0)
+declare void @putch(i32 %p0)
+declare void @putfloat(float %p0)
+declare i32 @getarray(i32* %p0)
+declare i32 @getfarray(float* %p0)
+declare void @putarray(i32 %p0, i32* %p1)
+declare void @putfarray(i32 %p0, float* %p1)
+declare void @_sysy_starttime(i32 %p0)
+declare void @_sysy_stoptime(i32 %p0)
+declare i32 @thrd_create(i32 %p0)
+declare void @thrd_join()
+declare void @putf()
+declare void @llvm.memset.p0.i32(i32* %p0, i8 %p1, i32 %p2, i1 %p3)
+define i32 @main() {
+entry:
+store i32 3, ptr @N
+store i32 3, ptr @M
+store i32 3, ptr @L
+%alloca_89 = alloca [3 x float]
+%alloca_90 = alloca [3 x float]
+%alloca_91 = alloca [3 x float]
+%alloca_92 = alloca [3 x float]
+%alloca_93 = alloca [3 x float]
+%alloca_94 = alloca [3 x float]
+%alloca_95 = alloca [6 x float]
+%alloca_96 = alloca [3 x float]
+%alloca_97 = alloca [3 x float]
+%getelementptr_303 = getelementptr [3 x float], ptr %alloca_94, i32 0
+%getelementptr_304 = getelementptr [3 x float], ptr %alloca_90, i32 0
+%getelementptr_305 = getelementptr [3 x float], ptr %alloca_91, i32 0
+%getelementptr_306 = getelementptr [3 x float], ptr %alloca_89, i32 0
+%getelementptr_307 = getelementptr [3 x float], ptr %alloca_92, i32 0
+%getelementptr_308 = getelementptr [3 x float], ptr %alloca_93, i32 0
+%call_309 = call i32 @thrd_create(i32 4)
+%Mul_311 = mul i32 %call_309, 3
+%SDiv_312 = sdiv i32 %Mul_311, 5
+%Add_314 = add i32 %Mul_311, 3
+%SDiv_315 = sdiv i32 %Add_314, 5
+br label %cond0
+
+cond0:
+%phi_224 = phi i32 [%SDiv_312, %entry], [%Add_135, %body1]
+%icmp_317 = icmp slt i32 %phi_224, %SDiv_315
+br i1 %icmp_317, label %body1, label %final2_split2
+
+body1:
+%getelementptr_105 = getelementptr [3 x float], ptr %getelementptr_306, i32 0, i32 %phi_224
+%itofp_107 = sitofp i32 %phi_224 to float
+store float %itofp_107, ptr %getelementptr_105
+%getelementptr_110 = getelementptr [3 x float], ptr %getelementptr_304, i32 0, i32 %phi_224
+store float %itofp_107, ptr %getelementptr_110
+%getelementptr_115 = getelementptr [3 x float], ptr %getelementptr_305, i32 0, i32 %phi_224
+store float %itofp_107, ptr %getelementptr_115
+%getelementptr_120 = getelementptr [3 x float], ptr %getelementptr_307, i32 0, i32 %phi_224
+store float %itofp_107, ptr %getelementptr_120
+%getelementptr_125 = getelementptr [3 x float], ptr %getelementptr_308, i32 0, i32 %phi_224
+store float %itofp_107, ptr %getelementptr_125
+%getelementptr_130 = getelementptr [3 x float], ptr %getelementptr_303, i32 0, i32 %phi_224
+store float %itofp_107, ptr %getelementptr_130
+%Add_135 = add i32 %phi_224, 1
+br label %cond0
+
+final2_split2:
+call void @thrd_join()
+%getelementptr_285 = getelementptr [3 x float], ptr %alloca_91, i32 0, i32 1
+%getelementptr_286 = getelementptr [3 x float], ptr %alloca_96, i32 0, i32 2
+%load_245 = load float, ptr %getelementptr_285
+store float %load_245, ptr %getelementptr_286
+%getelementptr_287 = getelementptr [3 x float], ptr %alloca_90, i32 0, i32 2
+%getelementptr_288 = getelementptr [3 x float], ptr %alloca_97, i32 0, i32 1
+%load_249 = load float, ptr %getelementptr_287
+store float %load_249, ptr %getelementptr_288
+%getelementptr_289 = getelementptr [3 x float], ptr %alloca_90, i32 0, i32 0
+%getelementptr_290 = getelementptr [6 x float], ptr %alloca_95, i32 0, i32 1
+%load_253 = load float, ptr %getelementptr_289
+store float %load_253, ptr %getelementptr_290
+%getelementptr_291 = getelementptr [3 x float], ptr %alloca_91, i32 0, i32 0
+%getelementptr_292 = getelementptr [6 x float], ptr %alloca_95, i32 0, i32 2
+%load_257 = load float, ptr %getelementptr_291
+store float %load_257, ptr %getelementptr_292
+%getelementptr_293 = getelementptr [3 x float], ptr %alloca_89, i32 0, i32 1
+%getelementptr_294 = getelementptr [3 x float], ptr %alloca_96, i32 0, i32 0
+%load_261 = load float, ptr %getelementptr_293
+store float %load_261, ptr %getelementptr_294
+%getelementptr_295 = getelementptr [3 x float], ptr %alloca_89, i32 0, i32 2
+%getelementptr_296 = getelementptr [3 x float], ptr %alloca_97, i32 0, i32 0
+%load_265 = load float, ptr %getelementptr_295
+store float %load_265, ptr %getelementptr_296
+%getelementptr_297 = getelementptr [3 x float], ptr %alloca_90, i32 0, i32 1
+%getelementptr_298 = getelementptr [3 x float], ptr %alloca_96, i32 0, i32 1
+%load_269 = load float, ptr %getelementptr_297
+store float %load_269, ptr %getelementptr_298
+%getelementptr_299 = getelementptr [3 x float], ptr %alloca_91, i32 0, i32 2
+%getelementptr_300 = getelementptr [3 x float], ptr %alloca_97, i32 0, i32 2
+%load_273 = load float, ptr %getelementptr_299
+store float %load_273, ptr %getelementptr_300
+%getelementptr_301 = getelementptr [3 x float], ptr %alloca_89, i32 0, i32 0
+%getelementptr_302 = getelementptr [6 x float], ptr %alloca_95, i32 0, i32 0
+%load_277 = load float, ptr %getelementptr_301
+store float %load_277, ptr %getelementptr_302
+%getelementptr_319 = getelementptr [6 x float], ptr %alloca_95, i32 0
+%call_320 = call i32 @thrd_create(i32 4)
+%Mul_322 = mul i32 %call_320, 3
+%SDiv_323 = sdiv i32 %Mul_322, 5
+%Add_325 = add i32 %Mul_322, 3
+%SDiv_326 = sdiv i32 %Add_325, 5
+br label %cond3
+
+cond3:
+%phi_225 = phi i32 [%SDiv_323, %final2_split2], [%Add_166, %body4]
+%icmp_328 = icmp slt i32 %phi_225, %SDiv_326
+br i1 %icmp_328, label %body4, label %final5
+
+body4:
+%getelementptr_159 = getelementptr [6 x float], ptr %getelementptr_319, i32 0, i32 %phi_225
+%load_160 = load float, ptr %getelementptr_159
+%fptoi_161 = fptosi float %load_160 to i32
+call void @putint(i32 %fptoi_161)
+%Add_166 = add i32 %phi_225, 1
+br label %cond3
+
+final5:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_330 = getelementptr [3 x float], ptr %alloca_96, i32 0
+%call_331 = call i32 @thrd_create(i32 4)
+%Mul_333 = mul i32 %call_331, 3
+%SDiv_334 = sdiv i32 %Mul_333, 5
+%Add_336 = add i32 %Mul_333, 3
+%SDiv_337 = sdiv i32 %Add_336, 5
+br label %cond6
+
+cond6:
+%phi_226 = phi i32 [%SDiv_334, %final5], [%Add_189, %body7]
+%icmp_339 = icmp slt i32 %phi_226, %SDiv_337
+br i1 %icmp_339, label %body7, label %final8
+
+body7:
+%getelementptr_182 = getelementptr [3 x float], ptr %getelementptr_330, i32 0, i32 %phi_226
+%load_183 = load float, ptr %getelementptr_182
+%fptoi_184 = fptosi float %load_183 to i32
+call void @putint(i32 %fptoi_184)
+%Add_189 = add i32 %phi_226, 1
+br label %cond6
+
+final8:
+call void @thrd_join()
+call void @putch(i32 10)
+%getelementptr_341 = getelementptr [3 x float], ptr %alloca_97, i32 0
+%call_342 = call i32 @thrd_create(i32 4)
+%Mul_344 = mul i32 %call_342, 3
+%SDiv_345 = sdiv i32 %Mul_344, 5
+%Add_347 = add i32 %Mul_344, 3
+%SDiv_348 = sdiv i32 %Add_347, 5
+br label %cond9
+
+cond9:
+%phi_227 = phi i32 [%SDiv_345, %final8], [%Add_212, %body10]
+%icmp_350 = icmp slt i32 %phi_227, %SDiv_348
+br i1 %icmp_350, label %body10, label %exit
+
+body10:
+%getelementptr_205 = getelementptr [3 x float], ptr %getelementptr_341, i32 0, i32 %phi_227
+%load_206 = load float, ptr %getelementptr_205
+%fptoi_207 = fptosi float %load_206 to i32
+call void @putint(i32 %fptoi_207)
+%Add_212 = add i32 %phi_227, 1
+br label %cond9
+
+exit:
+call void @thrd_join()
+call void @putch(i32 10)
+ret i32 0
+
+
+}
diff --git a/quick_test/log/3.log b/quick_test/log/3.log
new file mode 100644
index 0000000..0b9bfea
--- /dev/null
+++ b/quick_test/log/3.log
@@ -0,0 +1,109 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 109 µs
+
+## Pass func_inline 
+
+Time elapsed = 4 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 17 µs
+
+## Pass load_elim 
+
+Time elapsed = 9 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 12 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 6 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 12 µs
+
+## Pass load_elim 
+
+Time elapsed = 6 µs
+
+## Pass store_elim 
+
+Time elapsed = 6 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 4 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 35 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 12 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 8 µs
+
+## Pass func_inline 
+
+Time elapsed = 1 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 9 µs
+
+## Pass load_elim 
+
+Time elapsed = 6 µs
+
+## Pass store_elim 
+
+Time elapsed = 7 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 4 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 25 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 11 µs
+
+## Pass block_fuse 
+
+Time elapsed = 3 µs
+
+[INFO] loop entry is made candidate Candidate {
+  indvar: %phi_30 = phi i32 [0, %entry], [%Add_14, %body1],
+  exit: br i1 %icmp_24, label %body1, label %exit,
+  init_val: 0,
+  init_bb: entry,
+  exit_val: 8,
+  exit_bb: exit,
+}!
+## Pass sink_code [CHANGED]
+
+Time elapsed = 48 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 33 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/log/6.log b/quick_test/log/6.log
new file mode 100644
index 0000000..ad10945
--- /dev/null
+++ b/quick_test/log/6.log
@@ -0,0 +1,101 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 72 µs
+
+## Pass func_inline 
+
+Time elapsed = 5 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 9 µs
+
+## Pass load_elim 
+
+Time elapsed = 8 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 12 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 4 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 5 µs
+
+## Pass load_elim 
+
+Time elapsed = 5 µs
+
+## Pass store_elim 
+
+Time elapsed = 5 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 2 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 42 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 5 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 6 µs
+
+## Pass func_inline 
+
+Time elapsed = 1 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 3 µs
+
+## Pass load_elim 
+
+Time elapsed = 5 µs
+
+## Pass store_elim 
+
+Time elapsed = 5 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 2 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 13 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 3 µs
+
+## Pass block_fuse 
+
+Time elapsed = 1 µs
+
+## Pass sink_code [CHANGED]
+
+Time elapsed = 16 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 2 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/log/7.log b/quick_test/log/7.log
new file mode 100644
index 0000000..2b2eebf
--- /dev/null
+++ b/quick_test/log/7.log
@@ -0,0 +1,101 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 72 µs
+
+## Pass func_inline 
+
+Time elapsed = 4 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 9 µs
+
+## Pass load_elim 
+
+Time elapsed = 13 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 13 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 5 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 5 µs
+
+## Pass load_elim 
+
+Time elapsed = 8 µs
+
+## Pass store_elim 
+
+Time elapsed = 6 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 3 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 58 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 6 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 7 µs
+
+## Pass func_inline 
+
+Time elapsed = 2 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 3 µs
+
+## Pass load_elim 
+
+Time elapsed = 8 µs
+
+## Pass store_elim 
+
+Time elapsed = 7 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 3 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 23 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 4 µs
+
+## Pass block_fuse 
+
+Time elapsed = 1 µs
+
+## Pass sink_code [CHANGED]
+
+Time elapsed = 18 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 3 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
+TOTAL: 0H-0M-0S-0us
diff --git a/quick_test/log/96_matrix_add.log b/quick_test/log/96_matrix_add.log
new file mode 100644
index 0000000..9b9caa2
--- /dev/null
+++ b/quick_test/log/96_matrix_add.log
@@ -0,0 +1,110 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 182 µs
+
+## Pass func_inline 
+
+Time elapsed = 4 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 31 µs
+
+## Pass load_elim [CHANGED]
+
+Time elapsed = 28 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 27 µs
+
+## Pass dead_code_elim [CHANGED]
+
+Time elapsed = 12 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 25 µs
+
+## Pass load_elim 
+
+Time elapsed = 19 µs
+
+## Pass store_elim 
+
+Time elapsed = 22 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 9 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 133 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 27 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 11 µs
+
+## Pass func_inline 
+
+Time elapsed = 2 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 20 µs
+
+## Pass load_elim 
+
+Time elapsed = 18 µs
+
+## Pass store_elim 
+
+Time elapsed = 23 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 8 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 88 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 28 µs
+
+## Pass block_fuse 
+
+Time elapsed = 6 µs
+
+[INFO] loop entry fails because %load_73 = load i32, ptr @M is not calculated before loop
+[INFO] loop entry does not have indvar
+[INFO] loop entry is made candidate Candidate {
+  indvar: %phi_142 = phi i32 [0, %entry], [%Add_132, %body1],
+  exit: br i1 %icmp_137, label %body1, label %exit,
+  init_val: 0,
+  init_bb: entry,
+  exit_val: 3,
+  exit_bb: exit,
+}!
+## Pass sink_code [CHANGED]
+
+Time elapsed = 92 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 43 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
diff --git a/quick_test/log/97_matrix_sub.log b/quick_test/log/97_matrix_sub.log
new file mode 100644
index 0000000..9d081e5
--- /dev/null
+++ b/quick_test/log/97_matrix_sub.log
@@ -0,0 +1,140 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 322 µs
+
+## Pass func_inline [CHANGED]
+
+Time elapsed = 106 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 73 µs
+
+## Pass load_elim 
+
+Time elapsed = 25 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 68 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 23 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 53 µs
+
+## Pass load_elim 
+
+Time elapsed = 21 µs
+
+## Pass store_elim 
+
+Time elapsed = 43 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 21 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 272 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 54 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 31 µs
+
+## Pass func_inline 
+
+Time elapsed = 6 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 41 µs
+
+## Pass load_elim 
+
+Time elapsed = 19 µs
+
+## Pass store_elim 
+
+Time elapsed = 41 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 20 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 151 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 44 µs
+
+## Pass block_fuse 
+
+Time elapsed = 12 µs
+
+[INFO] loop entry is made candidate Candidate {
+  indvar: %phi_217 = phi i32 [0, %entry], [%Add_131, %body1],
+  exit: br i1 %icmp_135, label %body1, label %entry_inline0,
+  init_val: 0,
+  init_bb: entry,
+  exit_val: 3,
+  exit_bb: entry_inline0,
+}!
+[INFO] loop entry_inline0 is made candidate Candidate {
+  indvar: %phi_238 = phi i32 [0, %entry_inline0], [%Add_267, %body1_inline4],
+  exit: br i1 %icmp_239, label %body1_inline4, label %final2_split5,
+  init_val: 0,
+  init_bb: entry_inline0,
+  exit_val: 3,
+  exit_bb: final2_split5,
+}!
+[INFO] loop final2_split5 is made candidate Candidate {
+  indvar: %phi_218 = phi i32 [0, %final2_split5], [%Add_161, %body4],
+  exit: br i1 %icmp_165, label %body4, label %final5,
+  init_val: 0,
+  init_bb: final2_split5,
+  exit_val: 3,
+  exit_bb: final5,
+}!
+[INFO] loop final5 is made candidate Candidate {
+  indvar: %phi_219 = phi i32 [0, %final5], [%Add_183, %body7],
+  exit: br i1 %icmp_187, label %body7, label %final8,
+  init_val: 0,
+  init_bb: final5,
+  exit_val: 3,
+  exit_bb: final8,
+}!
+[INFO] loop final8 is made candidate Candidate {
+  indvar: %phi_220 = phi i32 [0, %final8], [%Add_205, %body10],
+  exit: br i1 %icmp_209, label %body10, label %exit,
+  init_val: 0,
+  init_bb: final8,
+  exit_val: 3,
+  exit_bb: exit,
+}!
+## Pass sink_code [CHANGED]
+
+Time elapsed = 132 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 95 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
diff --git a/quick_test/log/98_matrix_mul.log b/quick_test/log/98_matrix_mul.log
new file mode 100644
index 0000000..1b3033d
--- /dev/null
+++ b/quick_test/log/98_matrix_mul.log
@@ -0,0 +1,132 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 346 µs
+
+## Pass func_inline [CHANGED]
+
+Time elapsed = 244 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 143 µs
+
+## Pass load_elim [CHANGED]
+
+Time elapsed = 85 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 101 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 28 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 64 µs
+
+## Pass load_elim 
+
+Time elapsed = 58 µs
+
+## Pass store_elim 
+
+Time elapsed = 66 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 26 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 672 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 58 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 35 µs
+
+## Pass func_inline 
+
+Time elapsed = 3 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 39 µs
+
+## Pass load_elim 
+
+Time elapsed = 32 µs
+
+## Pass store_elim 
+
+Time elapsed = 49 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 18 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 284 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 43 µs
+
+## Pass block_fuse 
+
+Time elapsed = 9 µs
+
+[INFO] loop entry is made candidate Candidate {
+  indvar: %phi_404 = phi i32 [0, %entry], [%Add_315, %body1],
+  exit: br i1 %icmp_320, label %body1, label %final2_split2,
+  init_val: 0,
+  init_bb: entry,
+  exit_val: 3,
+  exit_bb: final2_split2,
+}!
+[INFO] loop final2_split2 is made candidate Candidate {
+  indvar: %phi_405 = phi i32 [0, %final2_split2], [%Add_346, %body4],
+  exit: br i1 %icmp_351, label %body4, label %final5,
+  init_val: 0,
+  init_bb: final2_split2,
+  exit_val: 3,
+  exit_bb: final5,
+}!
+[INFO] loop final5 is made candidate Candidate {
+  indvar: %phi_406 = phi i32 [0, %final5], [%Add_369, %body7],
+  exit: br i1 %icmp_374, label %body7, label %final8,
+  init_val: 0,
+  init_bb: final5,
+  exit_val: 3,
+  exit_bb: final8,
+}!
+[INFO] loop final8 is made candidate Candidate {
+  indvar: %phi_407 = phi i32 [0, %final8], [%Add_392, %body10],
+  exit: br i1 %icmp_397, label %body10, label %exit,
+  init_val: 0,
+  init_bb: final8,
+  exit_val: 3,
+  exit_bb: exit,
+}!
+## Pass sink_code [CHANGED]
+
+Time elapsed = 134 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 69 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
diff --git a/quick_test/log/99_matrix_tran.log b/quick_test/log/99_matrix_tran.log
new file mode 100644
index 0000000..7fcbfae
--- /dev/null
+++ b/quick_test/log/99_matrix_tran.log
@@ -0,0 +1,132 @@
+stdout:
+## Pass mem2reg [CHANGED]
+
+Time elapsed = 420 µs
+
+## Pass func_inline [CHANGED]
+
+Time elapsed = 150 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 92 µs
+
+## Pass load_elim [CHANGED]
+
+Time elapsed = 62 µs
+
+## Pass store_elim [CHANGED]
+
+Time elapsed = 79 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 24 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 46 µs
+
+## Pass load_elim 
+
+Time elapsed = 30 µs
+
+## Pass store_elim 
+
+Time elapsed = 54 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 20 µs
+
+## Pass redundance_elim [CHANGED]
+
+Time elapsed = 235 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 45 µs
+
+## Pass block_fuse [CHANGED]
+
+Time elapsed = 25 µs
+
+## Pass func_inline 
+
+Time elapsed = 2 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 30 µs
+
+## Pass load_elim 
+
+Time elapsed = 29 µs
+
+## Pass store_elim 
+
+Time elapsed = 55 µs
+
+## Pass dead_code_elim 
+
+Time elapsed = 17 µs
+
+## Pass redundance_elim 
+
+Time elapsed = 166 µs
+
+## Pass symbolic_eval 
+
+Time elapsed = 34 µs
+
+## Pass block_fuse 
+
+Time elapsed = 9 µs
+
+[INFO] loop entry is made candidate Candidate {
+  indvar: %phi_224 = phi i32 [0, %entry], [%Add_135, %body1],
+  exit: br i1 %icmp_140, label %body1, label %final2_split2,
+  init_val: 0,
+  init_bb: entry,
+  exit_val: 3,
+  exit_bb: final2_split2,
+}!
+[INFO] loop final2_split2 is made candidate Candidate {
+  indvar: %phi_225 = phi i32 [0, %final2_split2], [%Add_166, %body4],
+  exit: br i1 %icmp_171, label %body4, label %final5,
+  init_val: 0,
+  init_bb: final2_split2,
+  exit_val: 3,
+  exit_bb: final5,
+}!
+[INFO] loop final5 is made candidate Candidate {
+  indvar: %phi_226 = phi i32 [0, %final5], [%Add_189, %body7],
+  exit: br i1 %icmp_194, label %body7, label %final8,
+  init_val: 0,
+  init_bb: final5,
+  exit_val: 3,
+  exit_bb: final8,
+}!
+[INFO] loop final8 is made candidate Candidate {
+  indvar: %phi_227 = phi i32 [0, %final8], [%Add_212, %body10],
+  exit: br i1 %icmp_217, label %body10, label %exit,
+  init_val: 0,
+  init_bb: final8,
+  exit_val: 3,
+  exit_bb: exit,
+}!
+## Pass sink_code [CHANGED]
+
+Time elapsed = 103 µs
+
+## Pass symbolic_eval [CHANGED]
+
+Time elapsed = 70 µs
+
+
+stderr:
+
+stdout:
+
+stderr:
+
diff --git a/quick_test/output/3.out b/quick_test/output/3.out
new file mode 100644
index 0000000..f05272c
--- /dev/null
+++ b/quick_test/output/3.out
@@ -0,0 +1,3 @@
+8: 0 0 0 0 0 0 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/output/6.out b/quick_test/output/6.out
new file mode 100644
index 0000000..aba0265
--- /dev/null
+++ b/quick_test/output/6.out
@@ -0,0 +1,3 @@
+8: 22 2 8 10 2 4 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/output/7.out b/quick_test/output/7.out
new file mode 100644
index 0000000..1be4e05
--- /dev/null
+++ b/quick_test/output/7.out
@@ -0,0 +1,4 @@
+8: 2 2 8 10 2 4 0 0
+8: 4 4 16 20 4 4 0 0
+
+0
\ No newline at end of file
diff --git a/quick_test/output/96_matrix_add.out b/quick_test/output/96_matrix_add.out
new file mode 100644
index 0000000..88589df
--- /dev/null
+++ b/quick_test/output/96_matrix_add.out
@@ -0,0 +1,2 @@
+
+ExitStatus(unix_wait_status(139))
\ No newline at end of file
diff --git a/quick_test/output/97_matrix_sub.out b/quick_test/output/97_matrix_sub.out
new file mode 100644
index 0000000..88589df
--- /dev/null
+++ b/quick_test/output/97_matrix_sub.out
@@ -0,0 +1,2 @@
+
+ExitStatus(unix_wait_status(139))
\ No newline at end of file
diff --git a/quick_test/output/98_matrix_mul.out b/quick_test/output/98_matrix_mul.out
new file mode 100644
index 0000000..88589df
--- /dev/null
+++ b/quick_test/output/98_matrix_mul.out
@@ -0,0 +1,2 @@
+
+ExitStatus(unix_wait_status(139))
\ No newline at end of file
diff --git a/quick_test/output/99_matrix_tran.out b/quick_test/output/99_matrix_tran.out
new file mode 100644
index 0000000..88589df
--- /dev/null
+++ b/quick_test/output/99_matrix_tran.out
@@ -0,0 +1,2 @@
+
+ExitStatus(unix_wait_status(139))
\ No newline at end of file
diff --git a/quick_test/sy/3.sy b/quick_test/sy/3.sy
new file mode 100644
index 0000000..be4dede
--- /dev/null
+++ b/quick_test/sy/3.sy
@@ -0,0 +1,17 @@
+#include "../../lib/thrd.h"
+#include "../../lib/sylib.h"
+
+int A[9];
+int B[9];
+int main()
+{
+    int i = 0;
+    getarray(A);
+    while (i < 8)
+    {
+        i = i + 1;
+        B[i] = A[i];
+    }
+    putarray(8, B);
+    return 0;
+}
\ No newline at end of file
diff --git a/quick_test/sy/6.sy b/quick_test/sy/6.sy
new file mode 100644
index 0000000..8b038fb
--- /dev/null
+++ b/quick_test/sy/6.sy
@@ -0,0 +1,13 @@
+#include "../../lib/thrd.h"
+#include "../../lib/sylib.h"
+
+int A[9] = {1, 1, 4, 5, 1, 4};
+int main()
+{
+    A[0] = 11;
+    int n = thrd_create(4);
+    A[n] = A[n] * 2;
+    thrd_join();
+    putarray(8, A);
+    return 0;
+}
\ No newline at end of file
diff --git a/quick_test/sy/7.sy b/quick_test/sy/7.sy
new file mode 100644
index 0000000..bef21ca
--- /dev/null
+++ b/quick_test/sy/7.sy
@@ -0,0 +1,16 @@
+#include "../../lib/thrd.h"
+#include "../../lib/sylib.h"
+
+int A[9] = {1, 1, 4, 5, 1, 4};
+int main()
+{
+    int n = thrd_create(4);
+    A[n] = A[n] * 2;
+    thrd_join();
+    putarray(8, A);
+    int m = thrd_create(4);
+    A[m] = A[m] * 2;
+    thrd_join();
+    putarray(8, A);
+    return 0;
+}
\ No newline at end of file
diff --git a/quick_test/sy/96_matrix_add.sy b/quick_test/sy/96_matrix_add.sy
new file mode 100644
index 0000000..cb18f86
--- /dev/null
+++ b/quick_test/sy/96_matrix_add.sy
@@ -0,0 +1,69 @@
+#include "../../lib/sylib.h"
+int M;
+int L;
+int N;
+
+int add(float a0[], float a1[], float a2[], float b0[], float b1[], float b2[], float c0[], float c1[], float c2[])
+{
+    int i;
+    i = 0;
+    while (i < M)
+    {
+        c0[i] = a0[i] + b0[i];
+        c1[i] = a1[i] + b1[i];
+        c2[i] = a2[i] + b2[i];
+        i = i + 1;
+    }
+
+    return 0;
+}
+
+int main()
+{
+    N = 3;
+    M = 3;
+    L = 3;
+    float a0[3], a1[3], a2[3], b0[3], b1[3], b2[3], c0[6], c1[3], c2[3];
+    int i;
+    i = 0;
+    while (i < M)
+    {
+        a0[i] = i;
+        a1[i] = i;
+        a2[i] = i;
+        b0[i] = i;
+        b1[i] = i;
+        b2[i] = i;
+        i = i + 1;
+    }
+    // i = add(a0, a1, a2, b0, b1, b2, c0, c1, c2);
+    // int x;
+    // while(i<N)
+    // {
+    //     x = c0[i];
+    //     putint(x);
+    //     i=i+1;
+    // }
+    // x = 10;
+    // putch(x);
+    // i=0;
+    // while(i<N)
+    // {
+    //     x = c1[i];
+    //     putint(x);
+    //     i=i+1;
+    // }
+    // x = 10;
+    // putch(x);
+    // i=0;
+    // while(i<N)
+    // {
+    //     x = c2[i];
+    //     putint(x);
+    //     i=i+1;
+    // }
+    // x = 10;
+    // putch(x);
+
+    return 0;
+}
diff --git a/quick_test/sy/97_matrix_sub.sy b/quick_test/sy/97_matrix_sub.sy
new file mode 100644
index 0000000..cf66810
--- /dev/null
+++ b/quick_test/sy/97_matrix_sub.sy
@@ -0,0 +1,73 @@
+#include "../../lib/sylib.h"
+int N;
+int M;
+int L;
+
+int sub(float a0[],float a1[], float a2[],float b0[],float b1[],float b2[],float c0[],float c1[],float c2[])
+{
+    int i;
+    i=0;
+    while(i<3)
+    {
+        c0[i]=a0[i]-b0[i];
+        c1[i]=a1[i]-b1[i];
+        c2[i]=a2[i]-b2[i];
+        i=i+1;
+    } 
+
+    return 0;
+
+}
+
+int main()
+{
+    N=3;
+    M=3;
+    L=3;
+    float a0[3], a1[3], a2[3], b0[3], b1[3], b2[3], c0[6], c1[3], c2[3];
+    int i;
+    i=0;
+    while(i<3)
+    {
+        a0[i]=i;
+        a1[i]=i;
+        a2[i]=i;
+        b0[i]=i;
+        b1[i]=i;
+        b2[i]=i;
+        i=i+1;
+    }
+    i=sub( a0, a1,  a2, b0, b1, b2, c0, c1, c2);
+    int x;
+    while(i<3)
+    {
+        x = c0[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    i=0;
+    putch(x);
+    while(i<3)
+    {
+        x = c1[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    i=0;
+    putch(x);
+    while(i<3)
+    {
+        x = c2[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x =10;
+    putch(x);
+
+    return 0;
+}
diff --git a/quick_test/sy/98_matrix_mul.sy b/quick_test/sy/98_matrix_mul.sy
new file mode 100644
index 0000000..6547813
--- /dev/null
+++ b/quick_test/sy/98_matrix_mul.sy
@@ -0,0 +1,75 @@
+#include "../../lib/sylib.h"
+int M;
+int L;
+int N;
+
+
+int mul(float a0[],float a1[], float a2[],float b0[],float b1[],float b2[],float c0[],float c1[],float c2[])
+{
+    int i;
+    i=0;
+    c0[0]=a0[0]*b0[0]+a0[1]*b1[0]+a0[2]*b2[0];
+    c0[1]=a0[0]*b0[1]+a0[1]*b1[1]+a0[2]*b2[1];
+    c0[2]=a0[0]*b0[2]+a0[1]*b1[2]+a0[2]*b2[2];
+    c1[0]=a1[0]*b0[0]+a1[1]*b1[0]+a1[2]*b2[0];
+    c1[1]=a1[0]*b0[1]+a1[1]*b1[1]+a1[2]*b2[1];
+    c1[2]=a1[0]*b0[2]+a1[1]*b1[2]+a1[2]*b2[2];
+    c2[0]=a2[0]*b0[0]+a2[1]*b1[0]+a2[2]*b2[0];
+    c2[1]=a2[0]*b0[1]+a2[1]*b1[1]+a2[2]*b2[1];
+    c2[2]=a2[0]*b0[2]+a2[1]*b1[2]+a2[2]*b2[2];
+
+    return 0;
+
+}
+
+int main()
+{
+    N=3;
+    M=3;
+    L=3;
+    float a0[3], a1[3], a2[3], b0[3], b1[3], b2[3], c0[6], c1[3], c2[3];
+    int i;
+    i=0;
+    while(i<M)
+    {
+        a0[i]=i;
+        a1[i]=i;
+        a2[i]=i;
+        b0[i]=i;
+        b1[i]=i;
+        b2[i]=i;
+        i=i+1;
+    }
+    i=mul( a0, a1,  a2, b0, b1, b2, c0, c1, c2);
+    int x;
+    while(i<N)
+    {
+        x = c0[i];
+        putint(x);
+        i=i+1;
+    }
+    x = 10;
+    i=0;
+    putch(x);
+    while(i<N)
+    {
+        x = c1[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    i=0;
+    putch(x);
+    while(i<N)
+    {
+        x = c2[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    putch(x);
+
+    return 0;
+}
diff --git a/quick_test/sy/99_matrix_tran.sy b/quick_test/sy/99_matrix_tran.sy
new file mode 100644
index 0000000..d9a34d9
--- /dev/null
+++ b/quick_test/sy/99_matrix_tran.sy
@@ -0,0 +1,75 @@
+#include "../../lib/sylib.h"
+int M;
+int L;
+int N;
+
+int tran(float a0[],float a1[], float a2[],float b0[],float b1[],float b2[],float c0[],float c1[],float c2[])
+{
+    int i;
+    i=0;
+    c1[2]=a2[1];
+    c2[1]=a1[2];
+    c0[1]=a1[0];
+    c0[2]=a2[0];
+    c1[0]=a0[1];
+    c2[0]=a0[2];
+    c1[1]=a1[1];
+    c2[2]=a2[2];
+    c0[0]=a0[0];
+
+    return 0;
+
+}
+
+int main()
+{
+    N=3;
+    M=3;
+    L=3;
+    float a0[3], a1[3], a2[3], b0[3], b1[3], b2[3], c0[6], c1[3], c2[3];
+    int i;
+    i=0;
+    while(i<M)
+    {
+        a0[i]=i;
+        a1[i]=i;
+        a2[i]=i;
+        b0[i]=i;
+        b1[i]=i;
+        b2[i]=i;
+        i=i+1;
+    }
+    i=tran( a0, a1,  a2, b0, b1, b2, c0, c1, c2);
+    int x;
+    while(i<N)
+    {
+        x = c0[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    putch(x);
+    i=0;
+    while(i<N)
+    {
+        x = c1[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    i=0;
+    putch(x);
+    while(i<N)
+    {
+        x = c2[i];
+        putint(x);
+       
+        i=i+1;
+    }
+    x = 10;
+    putch(x);
+
+    return 0;
+}