removed old examples

This commit is contained in:
JanLJL
2019-08-06 18:27:53 +02:00
parent 7e7027e91d
commit 7b59303cf9
9 changed files with 0 additions and 557 deletions

View File

@@ -1,286 +0,0 @@
# mark_description "Intel(R) C Intel(R) 64 Compiler for applications running on Intel(R) 64, Version 17.0.5.239 Build 20170817";
# mark_description "-fno-alias -O3 -fopenmp -xCORE-AVX-I -S -o 2d.S";
.file "2d-5pt.c"
.text
..TXTST0:
# -- Begin jacobi2D5pt
.text
# mark_begin;
.align 16,0x90
.globl jacobi2D5pt
# --- jacobi2D5pt(int, int)
jacobi2D5pt:
# parameter 1: %edi
# parameter 2: %esi
..B1.1: # Preds ..B1.0
# Execution count [1.00e+00]
.cfi_startproc
..___tag_value_jacobi2D5pt.1:
..L2:
#2.31
pushq %rbx #2.31
.cfi_def_cfa_offset 16
movq %rsp, %rbx #2.31
.cfi_def_cfa 3, 16
.cfi_offset 3, -16
andq $-32, %rsp #2.31
pushq %rbp #2.31
pushq %rbp #2.31
movq 8(%rbx), %rbp #2.31
movq %rbp, 8(%rsp) #2.31
movq %rsp, %rbp #2.31
.cfi_escape 0x10, 0x06, 0x02, 0x76, 0x00
pushq %r13 #2.31
pushq %r14 #2.31
pushq %r15 #2.31
subq $88, %rsp #2.31
movslq %esi, %rsi #2.31
movslq %edi, %rcx #2.31
.cfi_escape 0x10, 0x0d, 0x02, 0x76, 0x78
.cfi_escape 0x10, 0x0e, 0x02, 0x76, 0x70
.cfi_escape 0x10, 0x0f, 0x02, 0x76, 0x68
movq %rsi, %r13 #4.17
imulq %rcx, %r13 #4.17
shlq $3, %r13 #4.12
movq %r13, %rax #4.12
addq $31, %rax #4.12
andq $-32, %rax #4.12
subq %rax, %rsp #4.12
movq %rsp, %rax #4.12
# LOE rax rcx rsi r12 r13 edi
..B1.29: # Preds ..B1.1
# Execution count [1.00e+00]
movq %rax, %r14 #4.12
# LOE rcx rsi r12 r13 r14 edi
..B1.2: # Preds ..B1.29
# Execution count [1.00e+00]
movq %r13, %rax #5.12
addq $31, %rax #5.12
andq $-32, %rax #5.12
subq %rax, %rsp #5.12
movq %rsp, %rax #5.12
# LOE rax rcx rsi r12 r13 r14 edi
..B1.30: # Preds ..B1.2
# Execution count [1.00e+00]
movq %rax, %r15 #5.12
# LOE rcx rsi r12 r13 r14 r15 edi
..B1.3: # Preds ..B1.30
# Execution count [1.00e+00]
xorl %r10d, %r10d #9.5
lea (%r15,%rcx,8), %r11 #13.13
vxorpd %xmm1, %xmm1, %xmm1 #6.5
lea (%r14,%rcx,8), %rdx #13.37
cmpq $2, %rsi #9.18
jle ..B1.21 # Prob 9% #9.18
# LOE rdx rcx rsi r10 r11 r12 r13 r14 r15 edi xmm1
..B1.4: # Preds ..B1.3
# Execution count [9.00e-01]
addl $-2, %edi #12.9
movq %rcx, %r9 #13.61
movl %edi, %eax #12.9
addq $-2, %rsi #9.18
andl $-16, %eax #12.9
xorl %r8d, %r8d #9.5
shlq $4, %r9 #13.61
movslq %eax, %rax #12.9
addq %r14, %r9 #13.61
movslq %edi, %rdi #12.9
vxorps %ymm0, %ymm0, %ymm0 #6.5
movq %rax, -80(%rbp) #12.9[spill]
movq %rdi, -88(%rbp) #12.9[spill]
movl %eax, -72(%rbp) #9.5[spill]
movq %rsi, -48(%rbp) #9.5[spill]
movq %rdx, -64(%rbp) #9.5[spill]
movq %r15, -96(%rbp) #9.5[spill]
movq %r14, -56(%rbp) #9.5[spill]
movq %r13, -104(%rbp) #9.5[spill]
movq %r12, -112(%rbp) #9.5[spill]
.cfi_escape 0x10, 0x0c, 0x03, 0x76, 0x90, 0x7f
# LOE rcx r8 r9 r10 r11 edi xmm1 ymm0
..B1.5: # Preds ..B1.19 ..B1.4
# Execution count [5.00e+00]
cmpq $2, %rcx #12.22
jle ..B1.19 # Prob 50% #12.22
# LOE rcx r8 r9 r10 r11 edi xmm1 ymm0
..B1.6: # Preds ..B1.5
# Execution count [4.50e+00]
cmpl $16, %edi #12.9
jl ..B1.26 # Prob 10% #12.9
# LOE rcx r8 r9 r10 r11 edi xmm1 ymm0
..B1.7: # Preds ..B1.6
# Execution count [4.50e+00]
movl -72(%rbp), %r14d #12.9[spill]
xorl %edx, %edx #12.9
movq -80(%rbp), %r12 #13.13[spill]
lea (%r11,%r8), %rax #13.13
# LOE rax rdx rcx r8 r9 r10 r11 r12 edi r14d xmm1 ymm0
..B1.8: # Preds ..B1.8 ..B1.7
# Execution count [2.50e+01]
vmovupd %ymm0, 8(%rax,%rdx,8) #13.13
vmovupd %ymm0, 40(%rax,%rdx,8) #13.13
vmovupd %ymm0, 72(%rax,%rdx,8) #13.13
vmovupd %ymm0, 104(%rax,%rdx,8) #13.13
addq $16, %rdx #12.9
cmpq %r12, %rdx #12.9
jb ..B1.8 # Prob 82% #12.9
# LOE rax rdx rcx r8 r9 r10 r11 r12 edi r14d xmm1 ymm0
..B1.10: # Preds ..B1.8 ..B1.26
# Execution count [5.00e+00]
lea 1(%r14), %eax #12.9
cmpl %edi, %eax #12.9
ja ..B1.19 # Prob 50% #12.9
# LOE rcx r8 r9 r10 r11 edi r14d xmm1 ymm0
..B1.11: # Preds ..B1.10
# Execution count [4.50e+00]
movslq %r14d, %r14 #12.9
movq -88(%rbp), %r13 #12.9[spill]
subq %r14, %r13 #12.9
cmpq $4, %r13 #12.9
jl ..B1.25 # Prob 10% #12.9
# LOE rcx r8 r9 r10 r11 r13 r14 edi xmm1 ymm0
..B1.12: # Preds ..B1.11
# Execution count [4.50e+00]
movl %r13d, %r15d #12.9
lea (%r11,%r8), %rax #13.13
andl $-4, %r15d #12.9
xorl %edx, %edx #12.9
movslq %r15d, %r15 #12.9
lea (%rax,%r14,8), %rax #13.13
# LOE rax rdx rcx r8 r9 r10 r11 r13 r14 r15 edi xmm1 ymm0
..B1.13: # Preds ..B1.13 ..B1.12
# Execution count [2.50e+01]
vmovupd %ymm0, 8(%rax,%rdx,8) #13.13
addq $4, %rdx #12.9
cmpq %r15, %rdx #12.9
jb ..B1.13 # Prob 82% #12.9
# LOE rax rdx rcx r8 r9 r10 r11 r13 r14 r15 edi xmm1 ymm0
..B1.15: # Preds ..B1.13 ..B1.25
# Execution count [5.00e+00]
cmpq %r13, %r15 #12.9
jae ..B1.19 # Prob 10% #12.9
# LOE rcx r8 r9 r10 r11 r13 r14 r15 edi xmm1 ymm0
..B1.16: # Preds ..B1.15
# Execution count [4.50e+00]
movq -56(%rbp), %rax #13.49[spill]
lea (%r11,%r8), %r12 #13.13
movq -64(%rbp), %rsi #13.25[spill]
lea (%r9,%r8), %rdx #13.61
lea (%r12,%r14,8), %r12 #13.13
addq %r8, %rax #13.49
addq %r8, %rsi #13.25
lea (%rdx,%r14,8), %rdx #13.61
lea (%rax,%r14,8), %rax #13.49
lea (%rsi,%r14,8), %r14 #13.25
# LOE rax rdx rcx r8 r9 r10 r11 r12 r13 r14 r15 edi xmm1 ymm0
movl $111, %ebx # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 100 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 103 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 144 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
..B1.17: # Preds ..B1.17 ..B1.16
# Execution count [2.50e+01]
vmovsd (%r14,%r15,8), %xmm2 #13.25
vaddsd 16(%r14,%r15,8), %xmm2, %xmm3 #13.37
vaddsd 8(%rax,%r15,8), %xmm3, %xmm4 #13.49
vaddsd 8(%rdx,%r15,8), %xmm4, %xmm5 #13.61
vmulsd %xmm5, %xmm1, %xmm6 #13.74
vmovsd %xmm6, 8(%r12,%r15,8) #13.13
incq %r15 #12.9
cmpq %r13, %r15 #12.9
jb ..B1.17 # Prob 82% #12.9
movl $222, %ebx # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 100 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 103 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
.byte 144 # INSERTED BY KERNCRAFT IACA MARKER UTILITY
# LOE rax rdx rcx r8 r9 r10 r11 r12 r13 r14 r15 edi xmm1 ymm0
..B1.19: # Preds ..B1.17 ..B1.5 ..B1.10 ..B1.15
# Execution count [5.00e+00]
incq %r10 #9.5
lea (%r8,%rcx,8), %r8 #9.5
cmpq -48(%rbp), %r10 #9.5[spill]
jb ..B1.5 # Prob 82% #9.5
# LOE rcx r8 r9 r10 r11 edi xmm1 ymm0
..B1.20: # Preds ..B1.19
# Execution count [9.00e-01]
movq -64(%rbp), %rdx #[spill]
movq -96(%rbp), %r15 #[spill]
movq -56(%rbp), %r14 #[spill]
movq -104(%rbp), %r13 #[spill]
movq -112(%rbp), %r12 #[spill]
.cfi_restore 12
# LOE rdx r11 r12 r13 r14 r15
..B1.21: # Preds ..B1.3 ..B1.20
# Execution count [1.00e+00]
addq $8, %rdx #16.5
addq $8, %r11 #16.5
movq %rdx, %rdi #16.5
movq %r11, %rsi #16.5
vzeroupper #16.5
..___tag_value_jacobi2D5pt.12:
# dummy(double *, double *)
call dummy #16.5
..___tag_value_jacobi2D5pt.13:
# LOE r12 r13 r14 r15
..B1.22: # Preds ..B1.21
# Execution count [1.00e+00]
movq %r15, %rdx #16.5
movq %r13, %rax #16.5
addq $31, %rax #16.5
andq $-32, %rax #16.5
addq %rax, %rsp #16.5
# LOE r12 r13 r14
..B1.23: # Preds ..B1.22
# Execution count [1.00e+00]
movq %r14, %rdx #16.5
movq %r13, %rax #16.5
addq $31, %rax #16.5
andq $-32, %rax #16.5
addq %rax, %rsp #16.5
# LOE r12
..B1.24: # Preds ..B1.23
# Execution count [1.00e+00]
lea -24(%rbp), %rsp #17.1
.cfi_restore 15
popq %r15 #17.1
.cfi_restore 14
popq %r14 #17.1
.cfi_restore 13
popq %r13 #17.1
popq %rbp #17.1
.cfi_restore 6
movq %rbx, %rsp #17.1
popq %rbx #17.1
.cfi_def_cfa 7, 8
.cfi_restore 3
ret #17.1
.cfi_def_cfa 3, 16
.cfi_offset 3, -16
.cfi_escape 0x10, 0x06, 0x02, 0x76, 0x00
.cfi_escape 0x10, 0x0c, 0x03, 0x76, 0x90, 0x7f
.cfi_escape 0x10, 0x0d, 0x02, 0x76, 0x78
.cfi_escape 0x10, 0x0e, 0x02, 0x76, 0x70
.cfi_escape 0x10, 0x0f, 0x02, 0x76, 0x68
# LOE
..B1.25: # Preds ..B1.11
# Execution count [4.50e-01]: Infreq
xorl %r15d, %r15d #12.9
jmp ..B1.15 # Prob 100% #12.9
# LOE rcx r8 r9 r10 r11 r13 r14 r15 edi xmm1 ymm0
..B1.26: # Preds ..B1.6
# Execution count [4.50e-01]: Infreq
xorl %r14d, %r14d #12.9
jmp ..B1.10 # Prob 100% #12.9
.align 16,0x90
# LOE rcx r8 r9 r10 r11 edi r14d xmm1 ymm0
.cfi_endproc
# mark_end;
.type jacobi2D5pt,@function
.size jacobi2D5pt,.-jacobi2D5pt
.data
# -- End jacobi2D5pt
.data
.section .note.GNU-stack, ""
// -- Begin DWARF2 SEGMENT .eh_frame
.section .eh_frame,"a",@progbits
.eh_frame_seg:
.align 8
# End

View File

@@ -1,16 +0,0 @@
void jacobi2D5pt(int N, int M){
void dummy(double*, double*);
double a[M][N];
double b[M][N];
double s;
for(int j=1; j<M-1; ++j){
#pragma vector aligned
//STARTLOOP
for(int i=1; i<N-1; ++i){
b[j][i] = ( a[j][i-1] + a[j][i+1] + a[j-1][i] + a[j+1][i]) * s;
}
}
dummy(&a[1][1], &b[1][1]);
}

View File

@@ -1,13 +0,0 @@
void daxpy(int N){
void dummy(double*, double*);
double a[N], b[N];
double s;
//STARTLOOP
for(int i=0; i<N; ++i)
a[i] = a[i] + s * b[i];
dummy(&a[1], &b[1]);
}

View File

@@ -1,13 +0,0 @@
void scale(int N){
void dummy(double*, double*);
double a[N], b[N];
double s;
//STARTLOOP
for(int i=0; i<N; ++i){
a[i] = s * b[i];
}
dummy(&a[1],&b[1]);
}

Binary file not shown.

Binary file not shown.

View File

@@ -1,199 +0,0 @@
# mark_description "Intel(R) C Intel(R) 64 Compiler for applications running on Intel(R) 64, Version 16.0.3.210 Build 20160415";
# mark_description "-I../../iaca-lin64/include -fno-alias -O3 -fopenmp -xCORE-AVX-I -S -o ivb-asm.S";
.file "taxCalc.c"
.text
..TXTST0:
# -- Begin main
.text
# mark_begin;
.align 16,0x90
.globl main
# --- main(void)
main:
..B1.1: # Preds ..B1.0
.cfi_startproc
..___tag_value_main.1:
..L2:
#4.15
pushq %rbp #4.15
.cfi_def_cfa_offset 16
movq %rsp, %rbp #4.15
.cfi_def_cfa 6, 16
.cfi_offset 6, -16
andq $-128, %rsp #4.15
subq $4096, %rsp #4.15
movl $104446, %esi #4.15
movl $3, %edi #4.15
call __intel_new_feature_proc_init #4.15
# LOE rbx r12 r13 r14 r15
..B1.10: # Preds ..B1.1
vstmxcsr (%rsp) #4.15
movl $.2.3_2_kmpc_loc_struct_pack.3, %edi #4.15
xorl %esi, %esi #4.15
orl $32832, (%rsp) #4.15
xorl %eax, %eax #4.15
vldmxcsr (%rsp) #4.15
..___tag_value_main.6:
call __kmpc_begin #4.15
..___tag_value_main.7:
# LOE rbx r12 r13 r14 r15
..B1.2: # Preds ..B1.10
movl $il0_peep_printf_format_0, %edi #5.5
call puts #5.5
# LOE rbx r12 r13 r14 r15
..B1.3: # Preds ..B1.2
vmovss .L_2il0floatpacket.0(%rip), %xmm0 #8.15
xorl %eax, %eax #11.5
vxorps %xmm1, %xmm1, %xmm1 #9.5
vmovss %xmm1, (%rsp) #9.5
movl $111,%ebx #IACA START
.byte 100,103,144 #IACA START
# LOE rax rbx r12 r13 r14 r15 xmm0 xmm1
..B1.4: # Preds ..B1.4 ..B1.3
lea 1(%rax,%rax), %edx #12.9
vcvtsi2ss %edx, %xmm2, %xmm2 #12.27
vmulss %xmm2, %xmm0, %xmm3 #12.29
lea 2(%rax,%rax), %ecx #12.9
vaddss %xmm3, %xmm1, %xmm4 #12.29
vxorps %xmm1, %xmm1, %xmm1 #12.27
vcvtsi2ss %ecx, %xmm1, %xmm1 #12.27
vmulss %xmm1, %xmm0, %xmm5 #12.29
vmovss %xmm4, 4(%rsp,%rax,8) #12.9
vaddss %xmm5, %xmm4, %xmm1 #12.29
vmovss %xmm1, 8(%rsp,%rax,8) #12.9
incq %rax #11.5
cmpq $499, %rax #11.5
jb ..B1.4 # Prob 99% #11.5
movl $222,%ebx #IACA END
.byte 100,103,144 #IACA END
# LOE rax rbx r12 r13 r14 r15 xmm0 xmm1
..B1.5: # Preds ..B1.4
vmovss 3992(%rsp), %xmm0 #12.18
movl $il0_peep_printf_format_1, %edi #15.5
vaddss .L_2il0floatpacket.1(%rip), %xmm0, %xmm1 #12.29
vmovss %xmm1, 3996(%rsp) #12.9
call puts #15.5
# LOE rbx r12 r13 r14 r15
..B1.6: # Preds ..B1.5
movl $.2.3_2_kmpc_loc_struct_pack.14, %edi #16.12
xorl %eax, %eax #16.12
..___tag_value_main.8:
call __kmpc_end #16.12
..___tag_value_main.9:
# LOE rbx r12 r13 r14 r15
..B1.7: # Preds ..B1.6
xorl %eax, %eax #16.12
movq %rbp, %rsp #16.12
popq %rbp #16.12
.cfi_def_cfa 7, 8
.cfi_restore 6
ret #16.12
.align 16,0x90
.cfi_endproc
# LOE
# mark_end;
.type main,@function
.size main,.-main
.data
.align 4
.align 4
.2.3_2_kmpc_loc_struct_pack.3:
.long 0
.long 2
.long 0
.long 0
.quad .2.3_2__kmpc_loc_pack.2
.align 4
.2.3_2__kmpc_loc_pack.2:
.byte 59
.byte 117
.byte 110
.byte 107
.byte 110
.byte 111
.byte 119
.byte 110
.byte 59
.byte 109
.byte 97
.byte 105
.byte 110
.byte 59
.byte 52
.byte 59
.byte 52
.byte 59
.byte 59
.space 1, 0x00 # pad
.align 4
.2.3_2_kmpc_loc_struct_pack.14:
.long 0
.long 2
.long 0
.long 0
.quad .2.3_2__kmpc_loc_pack.13
.align 4
.2.3_2__kmpc_loc_pack.13:
.byte 59
.byte 117
.byte 110
.byte 107
.byte 110
.byte 111
.byte 119
.byte 110
.byte 59
.byte 109
.byte 97
.byte 105
.byte 110
.byte 59
.byte 49
.byte 54
.byte 59
.byte 49
.byte 54
.byte 59
.byte 59
.section .rodata.str1.4, "aMS",@progbits,1
.align 4
.align 4
il0_peep_printf_format_0:
.long 1128354639
.long 1702109249
.long 1931506803
.long 1953653108
.byte 0
.space 3, 0x00 # pad
.align 4
il0_peep_printf_format_1:
.long 1128354639
.long 1702109249
.long 1696625779
.word 25710
.byte 0
.data
# -- End main
.section .rodata, "a"
.align 4
.align 4
.L_2il0floatpacket.0:
.long 0x3e428f5c
.type .L_2il0floatpacket.0,@object
.size .L_2il0floatpacket.0,4
.align 4
.L_2il0floatpacket.1:
.long 0x433dcf5c
.type .L_2il0floatpacket.1,@object
.size .L_2il0floatpacket.1,4
.data
.section .note.GNU-stack, ""
// -- Begin DWARF2 SEGMENT .eh_frame
.section .eh_frame,"a",@progbits
.eh_frame_seg:
.align 8
# End

View File

@@ -1,18 +0,0 @@
#include <stdio.h>
//#include "iacaMarks.h"
int main(void){
printf("OSACA test start\n");
int i = 1;
float arr[1000];
float tax = 0.19;
arr[0] = 0;
//STARTLOOP
while(i < 1000){
arr[i] = arr[i-1]+i*tax;
i += 1;
}
printf("OSACA test end\n");
return 0;
}

View File

@@ -1,12 +0,0 @@
void triad(int N){
void dummy(double*);
double a[N], b[N], c[N], d[N];
double s;
//STARTLOOP
for(int i=0; i<N; ++i)
a[i] = b[i] + c[i] * d[i];
dummy(&a[1]);
}