system stringclasses 7
values | input stringlengths 10 94.5k | output stringlengths 14 55.5k |
|---|---|---|
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z7x_dot_wPfS_S_jjj
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R0, SR_TID.Y ; /* 0x0000000000007919 */
/* 0x000e220000002200 */
/*0020... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z7x_dot_wPfS_S_jjj
.globl _Z7x_dot_wPfS_S_jjj
.p2align 8
.type _Z7x_dot_wPfS_S_jjj,@function
_Z7x_dot_wPfS_S_jjj:
s_clause 0x2
s_load_b32 s2, s[0:1], 0x34
s_load_b64 s[8:9], s[0:1], 0x18
s_load_b32 s3, s[0:1], 0x20
v_dual_mov_b32 v6,... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_0003e1ff_00000000-6_x_dot_w_tile.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2029:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, ... | .text
.file "x_dot_w_tile.hip"
.globl _Z22__device_stub__x_dot_wPfS_S_jjj # -- Begin function _Z22__device_stub__x_dot_wPfS_S_jjj
.p2align 4, 0x90
.type _Z22__device_stub__x_dot_wPfS_S_jjj,@function
_Z22__device_stub__x_dot_wPfS_S_jjj: # @_Z22__device_stub__x_dot_wPfS_S_jjj
.cfi_startproc
# %bb.0:
subq $152, %rsp
.c... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <cuda.h>
#include <cuda_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
__global__
void sumTriangle(float *M, float *V, int N)
{
int j = threadIdx.x;
int i;
float sum = 0;
for (i = 0; i <= j; ++i)
{
sum += M[i * N + j];
}
V[j] = sum;
__syncthreads();
if (j == N - 1)
{
sum = 0.0;
for (i = 0... | .file "tmpxft_0019af68_00000000-6_3_synchronization.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <cuda.h>
#include <cuda_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
__global__
void sumTriangle(float *M, float *V, int N)
{
int j = threadIdx.x;
int i;
float sum = 0;
for (i = 0; i <= j; ++i)
{
sum += M[i * N + j];
}
V[j] = sum;
__syncthreads();
if (j == N - 1)
{
sum = 0.0;
for (i = 0... | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
__global__
void sumTriangle(float *M, float *V, int N)
{
int j = threadIdx.x;
int i;
float sum = 0;
for (i = 0; i <= j; ++i)
{
sum += M[i * N + j];
}
V[j] = sum;
__syncthreads();
if (j == N - 1)
{
sum = 0.0;
for (i = 0; i < N; ++i)
{... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
__global__
void sumTriangle(float *M, float *V, int N)
{
int j = threadIdx.x;
int i;
float sum = 0;
for (i = 0; i <= j; ++i)
{
sum += M[i * N + j];
}
V[j] = sum;
__syncthreads();
if (j == N - 1)
{
sum = 0.0;
for (i = 0; i < N; ++i)
{... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z11sumTrianglePfS_i
.globl _Z11sumTrianglePfS_i
.p2align 8
.type _Z11sumTrianglePfS_i,@function
_Z11sumTrianglePfS_i:
s_clause 0x1
s_load_b32 s4, s[0:1], 0x10
s_load_b64 s[2:3], s[0:1], 0x0
v_lshlrev_b32_e32 v1, 2, v0
v_mov_b32_e32 v3,... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
__global__
void sumTriangle(float *M, float *V, int N)
{
int j = threadIdx.x;
int i;
float sum = 0;
for (i = 0; i <= j; ++i)
{
sum += M[i * N + j];
}
V[j] = sum;
__syncthreads();
if (j == N - 1)
{
sum = 0.0;
for (i = 0; i < N; ++i)
{... | .text
.file "3_synchronization.hip"
.globl _Z26__device_stub__sumTrianglePfS_i # -- Begin function _Z26__device_stub__sumTrianglePfS_i
.p2align 4, 0x90
.type _Z26__device_stub__sumTrianglePfS_i,@function
_Z26__device_stub__sumTrianglePfS_i: # @_Z26__device_stub__sumTrianglePfS_i
.cfi_startproc
# %bb.0:
subq $104, %r... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_0019af68_00000000-6_3_synchronization.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq... | .text
.file "3_synchronization.hip"
.globl _Z26__device_stub__sumTrianglePfS_i # -- Begin function _Z26__device_stub__sumTrianglePfS_i
.p2align 4, 0x90
.type _Z26__device_stub__sumTrianglePfS_i,@function
_Z26__device_stub__sumTrianglePfS_i: # @_Z26__device_stub__sumTrianglePfS_i
.cfi_startproc
# %bb.0:
subq $104, %r... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | /*
* Copyright (c) 2019 Opticks Team. All Rights Reserved.
*
* This file is part of Opticks
* (see https://bitbucket.org/simoncblyth/opticks).
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License a... | /*
* Copyright (c) 2019 Opticks Team. All Rights Reserved.
*
* This file is part of Opticks
* (see https://bitbucket.org/simoncblyth/opticks).
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License a... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <iostream>
#include <cmath>
#include <functional>
#include <random>
#include <sys/time.h>
#include <thrust/host_vector.h>
#include <thrust/device_vector.h>
#include <thrust/transform_reduce.h>
#include <thrust/generate.h>
#define N 4
double wtime()
{
struct timeval t;
gettimeofday (&t, NULL);
return (double)t.... | code for sm_80
Function : _ZN3cub17CUB_200700_800_NS6detail8for_each13static_kernelINS2_12policy_hub_t12policy_350_tElN6thrust20THRUST_200700_800_NS8cuda_cub11__transform18binary_transform_fINS7_6detail15normal_iteratorINS7_10device_ptrIfEEEESF_SF_NS9_14no_stencil_tagENS7_4plusIfEENS9_21always_true_predicateEEEEEvT0_T1... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <iostream>
#include <cmath>
#include <functional>
#include <random>
#include <sys/time.h>
#include <thrust/host_vector.h>
#include <thrust/device_vector.h>
#include <thrust/transform_reduce.h>
#include <thrust/generate.h>
#define N 4
double wtime()
{
struct timeval t;
gettimeofday (&t, NULL);
return (double)t.... | #include <hip/hip_runtime.h>
#include <iostream>
#include <cmath>
#include <functional>
#include <random>
#include <sys/time.h>
#include <thrust/host_vector.h>
#include <thrust/device_vector.h>
#include <thrust/transform_reduce.h>
#include <thrust/generate.h>
#define N 4
double wtime()
{
struct timeval t;
gettimeofday ... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <iostream>
#include <cmath>
#include <functional>
#include <random>
#include <sys/time.h>
#include <thrust/host_vector.h>
#include <thrust/device_vector.h>
#include <thrust/transform_reduce.h>
#include <thrust/generate.h>
#define N 4
double wtime()
{
struct timeval t;
gettimeofday ... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.section .text._ZN6thrust11hip_rocprim14__parallel_for6kernelILj256ENS0_11__transform18binary_transform_fINS_6detail15normal_iteratorINS_10device_ptrIfEEEES9_S9_NS3_14no_stencil_tagENS_4plusIfEENS3_21always_true_predicateEEElLj1EEEvT0_T1_SG_,"axG",@progbits,_ZN6thrust11... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _ZN3cub17CUB_200700_800_NS6detail8for_each13static_kernelINS2_12policy_hub_t12policy_350_tElN6thrust20THRUST_200700_800_NS8cuda_cub11__transform18binary_transform_fINS7_6detail15normal_iteratorINS7_10device_ptrIfEEEESF_SF_NS9_14no_stencil_tagENS7_4plusIfEENS9_21always_true_predicateEEEEEvT0_T1... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.section .text._ZN6thrust11hip_rocprim14__parallel_for6kernelILj256ENS0_11__transform18binary_transform_fINS_6detail15normal_iteratorINS_10device_ptrIfEEEES9_S9_NS3_14no_stencil_tagENS_4plusIfEENS3_21always_true_predicateEEElLj1EEEvT0_T1_SG_,"axG",@progbits,_ZN6thrust11... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include "includes.h"
__device__ inline static float euclid_distance(int numCoords, int numObjs, int numClusters, int tid, int clusterId, float *objects, float *clusters )
{
float ans=0.0;
for (int i = 0; i < numCoords; i++) {
ans += (objects[3*tid+i] - clusters[i + clusterId*3]) *
(objects[3*tid+i] - clusters[i + clus... | .file "tmpxft_001274b3_00000000-6_find_nearest_cluster.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2030:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
a... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include "includes.h"
__device__ inline static float euclid_distance(int numCoords, int numObjs, int numClusters, int tid, int clusterId, float *objects, float *clusters )
{
float ans=0.0;
for (int i = 0; i < numCoords; i++) {
ans += (objects[3*tid+i] - clusters[i + clusterId*3]) *
(objects[3*tid+i] - clusters[i + clus... | #include <hip/hip_runtime.h>
#include "includes.h"
__device__ inline static float euclid_distance(int numCoords, int numObjs, int numClusters, int tid, int clusterId, float *objects, float *clusters )
{
float ans=0.0;
for (int i = 0; i < numCoords; i++) {
ans += (objects[3*tid+i] - clusters[i + clusterId*3]) *
(objects... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include "includes.h"
__device__ inline static float euclid_distance(int numCoords, int numObjs, int numClusters, int tid, int clusterId, float *objects, float *clusters )
{
float ans=0.0;
for (int i = 0; i < numCoords; i++) {
ans += (objects[3*tid+i] - clusters[i + clusterId*3]) *
(objects... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.section .text._ZL20find_nearest_clusteriiiPfS_PiS0_,"axG",@progbits,_ZL20find_nearest_clusteriiiPfS_PiS0_,comdat
.globl _ZL20find_nearest_clusteriiiPfS_PiS0_
.p2align 8
.type _ZL20find_nearest_clusteriiiPfS_PiS0_,@function
_ZL20find_nearest_clusteriiiPfS_PiS0_:
s_cl... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include "includes.h"
__device__ inline static float euclid_distance(int numCoords, int numObjs, int numClusters, int tid, int clusterId, float *objects, float *clusters )
{
float ans=0.0;
for (int i = 0; i < numCoords; i++) {
ans += (objects[3*tid+i] - clusters[i + clusterId*3]) *
(objects... | .text
.file "find_nearest_cluster.hip"
.type __hip_cuid_,@object # @__hip_cuid_
.bss
.globl __hip_cuid_
__hip_cuid_:
.byte 0 # 0x0
.size __hip_cuid_, 1
.section ".linker-options","e",@llvm_linker_options
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_001274b3_00000000-6_find_nearest_cluster.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2030:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
a... | .text
.file "find_nearest_cluster.hip"
.type __hip_cuid_,@object # @__hip_cuid_
.bss
.globl __hip_cuid_
__hip_cuid_:
.byte 0 # 0x0
.size __hip_cuid_, 1
.section ".linker-options","e",@llvm_linker_options
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <stdio.h>
#include <cuda.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix->cols * row... | code for sm_80 |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <stdio.h>
#include <cuda.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix->cols * row... | .file "tmpxft_00096d7d_00000000-6_matrix-multiply.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2072:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <stdio.h>
#include <cuda.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix->cols * row... | #include <stdio.h>
#include <hip/hip_runtime.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix-... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <stdio.h>
#include <hip/hip_runtime.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix-... | .text
.p2alignl 7, 3214868480
.fill 96, 4, 3214868480
.type __hip_cuid_,@object
.section .bss,"aw",@nobits
.globl __hip_cuid_
__hip_cuid_:
.byte 0
.size __hip_cuid_, 1
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.3.2 25012 e5bf7... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <stdio.h>
#include <hip/hip_runtime.h>
typedef float MatrixVal;
typedef struct matrix {
MatrixVal *values;
unsigned int rows, cols;
} Matrix;
typedef struct input {
Matrix *A, *B;
} Input;
void setMatrixPosition(Matrix *matrix, unsigned int row, unsigned int col, MatrixVal value) {
matrix->values[col + matrix-... | .text
.file "matrix-multiply.hip"
.globl _Z17setMatrixPositionP6matrixjjf # -- Begin function _Z17setMatrixPositionP6matrixjjf
.p2align 4, 0x90
.type _Z17setMatrixPositionP6matrixjjf,@function
_Z17setMatrixPositionP6matrixjjf: # @_Z17setMatrixPositionP6matrixjjf
.cfi_startproc
# %bb.0:
... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80 | .text
.p2alignl 7, 3214868480
.fill 96, 4, 3214868480
.type __hip_cuid_,@object
.section .bss,"aw",@nobits
.globl __hip_cuid_
__hip_cuid_:
.byte 0
.size __hip_cuid_, 1
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.3.2 25012 e5bf7... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_00096d7d_00000000-6_matrix-multiply.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2072:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $... | .text
.file "matrix-multiply.hip"
.globl _Z17setMatrixPositionP6matrixjjf # -- Begin function _Z17setMatrixPositionP6matrixjjf
.p2align 4, 0x90
.type _Z17setMatrixPositionP6matrixjjf,@function
_Z17setMatrixPositionP6matrixjjf: # @_Z17setMatrixPositionP6matrixjjf
.cfi_startproc
# %bb.0:
... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB, float* dC, float alpha, int... | code for sm_80
Function : _Z6streamPfS_S_fi
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R6, SR_CTAID.X ; /* 0x0000000000067919 */
/* 0x000e280000002500 */
/*0020... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB, float* dC, float alpha, int... | .file "tmpxft_00070361_00000000-6_stream.kernel.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2030:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8,... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB, float* dC, float alpha, int... | #include <hip/hip_runtime.h>
#ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z6streamPfS_S_fi
.globl _Z6streamPfS_S_fi
.p2align 8
.type _Z6streamPfS_S_fi,@function
_Z6streamPfS_S_fi:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x2c
s_load_b32 s3, s[0:1], 0x1c
s_waitcnt lgkmcnt(0)
s_and_b32 s2, s2, 0xffff
s_delay_... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#ifndef THREADS_PER_BLOCK
#define THREADS_PER_BLOCK 1024
#endif
__global__ void stream(float* dA, float* dB, float* dC, float alpha, int N) {
int id = blockIdx.x * blockDim.x + threadIdx.x;
if (id < N) {
dA[id] = dB[id] + alpha*dC[id];
}
}
extern "C" {
void LaunchStream(float* dA, float *dB... | .text
.file "stream.kernel.hip"
.globl _Z21__device_stub__streamPfS_S_fi # -- Begin function _Z21__device_stub__streamPfS_S_fi
.p2align 4, 0x90
.type _Z21__device_stub__streamPfS_S_fi,@function
_Z21__device_stub__streamPfS_S_fi: # @_Z21__device_stub__streamPfS_S_fi
.cfi_startproc
# %bb.0:
subq $120, %rsp
.cfi_def_... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z6streamPfS_S_fi
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R6, SR_CTAID.X ; /* 0x0000000000067919 */
/* 0x000e280000002500 */
/*0020... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z6streamPfS_S_fi
.globl _Z6streamPfS_S_fi
.p2align 8
.type _Z6streamPfS_S_fi,@function
_Z6streamPfS_S_fi:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x2c
s_load_b32 s3, s[0:1], 0x1c
s_waitcnt lgkmcnt(0)
s_and_b32 s2, s2, 0xffff
s_delay_... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_00070361_00000000-6_stream.kernel.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2030:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8,... | .text
.file "stream.kernel.hip"
.globl _Z21__device_stub__streamPfS_S_fi # -- Begin function _Z21__device_stub__streamPfS_S_fi
.p2align 4, 0x90
.type _Z21__device_stub__streamPfS_S_fi,@function
_Z21__device_stub__streamPfS_S_fi: # @_Z21__device_stub__streamPfS_S_fi
.cfi_startproc
# %bb.0:
subq $120, %rsp
.cfi_def_... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <iostream>
#include <vector>
#include <cuda.h>
#include <cuda_runtime.h>
using namespace std;
#define CUDA_CALL( call ) \
{ \
cudaError_t err = call; \
if ( cudaSuccess != err) \
fprintf(stderr, "CUDA error for %s in %d of %s : %s.\n", #call , __LINE__ , __FILE__ ,cudaGetErrorString(err));\
}
__global__ void p... | .file "tmpxft_00077a02_00000000-6_bb.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB4039:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregis... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <iostream>
#include <vector>
#include <cuda.h>
#include <cuda_runtime.h>
using namespace std;
#define CUDA_CALL( call ) \
{ \
cudaError_t err = call; \
if ( cudaSuccess != err) \
fprintf(stderr, "CUDA error for %s in %d of %s : %s.\n", #call , __LINE__ , __FILE__ ,cudaGetErrorString(err));\
}
__global__ void p... | #include <iostream>
#include <vector>
#include <hip/hip_runtime.h>
using namespace std;
#define CUDA_CALL( call ) \
{ \
hipError_t err = call; \
if ( hipSuccess != err) \
fprintf(stderr, "CUDA error for %s in %d of %s : %s.\n", #call , __LINE__ , __FILE__ ,hipGetErrorString(err));\
}
__global__ void printLinearVector_G... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <iostream>
#include <vector>
#include <hip/hip_runtime.h>
using namespace std;
#define CUDA_CALL( call ) \
{ \
hipError_t err = call; \
if ( hipSuccess != err) \
fprintf(stderr, "CUDA error for %s in %d of %s : %s.\n", #call , __LINE__ , __FILE__ ,hipGetErrorString(err));\
}
__global__ void printLinearVector_G... | .text
.file "bb.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z36__device_stub__printLinearVector_GPUPmmmm # -- Begin function _Z36__device_stub__printLinearVector_G... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + y * width] = matrixOrigin[y +... | code for sm_80
Function : _Z5saxpyPfS_f
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R2, SR_CTAID.X ; /* 0x0000000000027919 */
/* 0x000e220000002500 */
/*0020*/ H... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + y * width] = matrixOrigin[y +... | .file "tmpxft_000fe4d0_00000000-6_cuda.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3774:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + y * width] = matrixOrigin[y +... | #include <hip/hip_runtime.h>
#include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + ... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + ... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z9transposePfS_
.globl _Z9transposePfS_
.p2align 8
.type _Z9transposePfS_,@function
_Z9transposePfS_:
s_clause 0x1
s_load_b32 s4, s[0:1], 0x1c
s_load_b32 s5, s[0:1], 0x10
v_and_b32_e32 v1, 0x3ff, v0
s_load_b128 s[0:3], s[0:1], ... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include <iostream>
#include <chrono>
const size_t size = 1 << 20;
__global__ void transpose(float_t *matrixOrigin, float_t *matrixRes) {
size_t x = blockIdx.x * blockDim.x + threadIdx.x;
size_t y = blockIdx.y * blockDim.y + threadIdx.y;
size_t width = gridDim.x * blockDim.x;
matrixRes[x + ... | .text
.file "cuda.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z24__device_stub__transposePfS_ # -- Begin function _Z24__device_stub__transposePfS_
.p2align 4, 0x90... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z5saxpyPfS_f
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R2, SR_CTAID.X ; /* 0x0000000000027919 */
/* 0x000e220000002500 */
/*0020*/ H... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z9transposePfS_
.globl _Z9transposePfS_
.p2align 8
.type _Z9transposePfS_,@function
_Z9transposePfS_:
s_clause 0x1
s_load_b32 s4, s[0:1], 0x1c
s_load_b32 s5, s[0:1], 0x10
v_and_b32_e32 v1, 0x3ff, v0
s_load_b128 s[0:3], s[0:1], ... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_000fe4d0_00000000-6_cuda.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3774:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... | .text
.file "cuda.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z24__device_stub__transposePfS_ # -- Begin function _Z24__device_stub__transposePfS_
.p2align 4, 0x90... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
their entire file nor did I want ... | code for sm_80
Function : _Z3addPfS_S_
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R0, SR_CTAID.X ; /* 0x0000000000007919 */
/* 0x000e240000002500 */
/*0020*/ IS... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
their entire file nor did I want ... | .file "tmpxft_0001aa86_00000000-6_vector_summation.cudafe1.cpp"
.text
#APP
.section .rodata.str1.1,"aMS",@progbits,1
.LC0:
.string "%s in %s at line %d\n"
#NO_APP
.text
.type _ZL11HandleError9cudaErrorPKci, @function
_ZL11HandleError9cudaErrorPKci:
.LFB2057:
.cfi_startproc
testl %edi, %edi
jne .L6
ret
.L6:
pushq %rbp
.... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
their entire file nor did I want ... | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <hip/hip_runtime.h>
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
thei... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <hip/hip_runtime.h>
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
thei... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z3addPfS_S_
.globl _Z3addPfS_S_
.p2align 8
.type _Z3addPfS_S_,@function
_Z3addPfS_S_:
s_cmpk_gt_i32 s15, 0x7fff
s_cbranch_scc1 .LBB0_3
s_clause 0x2
s_load_b128 s[4:7], s[0:1], 0x0
s_load_b64 s[8:9], s[0:1], 0x10
s_load_... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | /*
* Shade Alabsa
* Vector Summation Example from Cuda By Example
* CS 7172
* Edward Jung
* HW 3
* Most is taken from the example in the book with little changes.
*/
#include <hip/hip_runtime.h>
#include <stdio.h>
#define N (32 * 1024)
/*
These error functions is ripped from there example. I didn't want to include
thei... | .text
.file "vector_summation.hip"
.globl _Z18__device_stub__addPfS_S_ # -- Begin function _Z18__device_stub__addPfS_S_
.p2align 4, 0x90
.type _Z18__device_stub__addPfS_S_,@function
_Z18__device_stub__addPfS_S_: # @_Z18__device_stub__addPfS_S_
.cfi_startproc
# %bb.0:
subq $104, %rsp
.cfi_def_cfa_offset 112... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z3addPfS_S_
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R0, SR_CTAID.X ; /* 0x0000000000007919 */
/* 0x000e240000002500 */
/*0020*/ IS... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z3addPfS_S_
.globl _Z3addPfS_S_
.p2align 8
.type _Z3addPfS_S_,@function
_Z3addPfS_S_:
s_cmpk_gt_i32 s15, 0x7fff
s_cbranch_scc1 .LBB0_3
s_clause 0x2
s_load_b128 s[4:7], s[0:1], 0x0
s_load_b64 s[8:9], s[0:1], 0x10
s_load_... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_0001aa86_00000000-6_vector_summation.cudafe1.cpp"
.text
#APP
.section .rodata.str1.1,"aMS",@progbits,1
.LC0:
.string "%s in %s at line %d\n"
#NO_APP
.text
.type _ZL11HandleError9cudaErrorPKci, @function
_ZL11HandleError9cudaErrorPKci:
.LFB2057:
.cfi_startproc
testl %edi, %edi
jne .L6
ret
.L6:
pushq %rbp
.... | .text
.file "vector_summation.hip"
.globl _Z18__device_stub__addPfS_S_ # -- Begin function _Z18__device_stub__addPfS_S_
.p2align 4, 0x90
.type _Z18__device_stub__addPfS_S_,@function
_Z18__device_stub__addPfS_S_: # @_Z18__device_stub__addPfS_S_
.cfi_startproc
# %bb.0:
subq $104, %rsp
.cfi_def_cfa_offset 112... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | //
// Threshold-based Contrasting GPU implementation
//
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrapper
unsigned char *gpu_flow_rec... | code for sm_80
Function : _Z23cuda_flow_bitmap_kernelPhS_jj
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ IMAD.MOV.U32 R1, RZ, RZ, c[0x0][0x28] ; /* 0x00000a00ff017624 */
/* 0x000fe400078e00ff */
/*0010*/ S2R R2, SR_TID.X ; /* 0x0000000000027919 */
... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | //
// Threshold-based Contrasting GPU implementation
//
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrapper
unsigned char *gpu_flow_rec... | .file "tmpxft_0003bb70_00000000-6_gpu_flow_recogu8.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2043:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq ... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | //
// Threshold-based Contrasting GPU implementation
//
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrapper
unsigned char *gpu_flow_rec... | //
// Threshold-based Contrasting GPU implementation
//
#include <hip/hip_runtime.h>
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrappe... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | //
// Threshold-based Contrasting GPU implementation
//
#include <hip/hip_runtime.h>
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrappe... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z23cuda_flow_bitmap_kernelPhS_jj
.globl _Z23cuda_flow_bitmap_kernelPhS_jj
.p2align 8
.type _Z23cuda_flow_bitmap_kernelPhS_jj,@function
_Z23cuda_flow_bitmap_kernelPhS_jj:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x24
s_load_b32 s3, s[0:1], 0x10
s_waitcnt lg... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | //
// Threshold-based Contrasting GPU implementation
//
#include <hip/hip_runtime.h>
#include <unistd.h>
#include <stdlib.h>
#define THREADS_PER_BLOCK 128
// CUDA kernel declaration
__global__ void cuda_flow_bitmap_kernel(unsigned char *u8data, unsigned char *u8res, unsigned int N, unsigned int thresh);
// C/C++ Wrappe... | .text
.file "gpu_flow_recogu8.hip"
.globl _Z23gpu_flow_recogu8_bitmapPhS_jj # -- Begin function _Z23gpu_flow_recogu8_bitmapPhS_jj
.p2align 4, 0x90
.type _Z23gpu_flow_recogu8_bitmapPhS_jj,@function
_Z23gpu_flow_recogu8_bitmapPhS_jj: # @_Z23gpu_flow_recogu8_bitmapPhS_jj
.cfi_startproc
# %bb.0:
pushq %rbp
.cfi_def_cf... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z23cuda_flow_bitmap_kernelPhS_jj
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ IMAD.MOV.U32 R1, RZ, RZ, c[0x0][0x28] ; /* 0x00000a00ff017624 */
/* 0x000fe400078e00ff */
/*0010*/ S2R R2, SR_TID.X ; /* 0x0000000000027919 */
... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z23cuda_flow_bitmap_kernelPhS_jj
.globl _Z23cuda_flow_bitmap_kernelPhS_jj
.p2align 8
.type _Z23cuda_flow_bitmap_kernelPhS_jj,@function
_Z23cuda_flow_bitmap_kernelPhS_jj:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x24
s_load_b32 s3, s[0:1], 0x10
s_waitcnt lg... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_0003bb70_00000000-6_gpu_flow_recogu8.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2043:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq ... | .text
.file "gpu_flow_recogu8.hip"
.globl _Z23gpu_flow_recogu8_bitmapPhS_jj # -- Begin function _Z23gpu_flow_recogu8_bitmapPhS_jj
.p2align 4, 0x90
.type _Z23gpu_flow_recogu8_bitmapPhS_jj,@function
_Z23gpu_flow_recogu8_bitmapPhS_jj: # @_Z23gpu_flow_recogu8_bitmapPhS_jj
.cfi_startproc
# %bb.0:
pushq %rbp
.cfi_def_cf... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < ... | code for sm_80
Function : _Z16fibonacci_kernelPmi
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R3, SR_CTAID.X ; /* 0x0000000000037919 */
/* 0x000e220000002500 */
... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < ... | .file "tmpxft_000f723a_00000000-6_main.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3676:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < ... | #include "hip/hip_runtime.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < 2 * start - 1)
a[index] = (a[start ... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include "hip/hip_runtime.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < 2 * start - 1)
a[index] = (a[start ... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z16fibonacci_kernelPmi
.globl _Z16fibonacci_kernelPmi
.p2align 8
.type _Z16fibonacci_kernelPmi,@function
_Z16fibonacci_kernelPmi:
s_clause 0x1
s_load_b32 s3, s[0:1], 0x1c
s_load_b32 s2, s[0:1], 0x8
s_waitcnt lgkmcnt(0)
s_and_b32 s3, s3, 0xff... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include "hip/hip_runtime.h"
#include <cstdlib>
#include <cstdio>
#include <cassert>
#include <iostream>
#define ULI unsigned long int
__global__ void fibonacci_kernel(ULI* a, int start) {
unsigned int i = blockIdx.x * blockDim.x + threadIdx.x;
unsigned int index = i + start;
if (i < 2 * start - 1)
a[index] = (a[start ... | .text
.file "main.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z31__device_stub__fibonacci_kernelPmi # -- Begin function _Z31__device_stub__fibonacci_kernelPmi
.p2a... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z16fibonacci_kernelPmi
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R3, SR_CTAID.X ; /* 0x0000000000037919 */
/* 0x000e220000002500 */
... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z16fibonacci_kernelPmi
.globl _Z16fibonacci_kernelPmi
.p2align 8
.type _Z16fibonacci_kernelPmi,@function
_Z16fibonacci_kernelPmi:
s_clause 0x1
s_load_b32 s3, s[0:1], 0x1c
s_load_b32 s2, s[0:1], 0x8
s_waitcnt lgkmcnt(0)
s_and_b32 s3, s3, 0xff... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_000f723a_00000000-6_main.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3676:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... | .text
.file "main.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z31__device_stub__fibonacci_kernelPmi # -- Begin function _Z31__device_stub__fibonacci_kernelPmi
.p2a... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
cudaMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times; ++i)
run<<<157, 64>>>(h_d)... | code for sm_80
Function : _Z3runPf
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R2, SR_CTAID.X ; /* 0x0000000000027919 */
/* 0x000e280000002500 */
/*0020*/ S2R R3... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
cudaMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times; ++i)
run<<<157, 64>>>(h_d)... | .file "tmpxft_00189640_00000000-6_main.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3672:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
cudaMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times; ++i)
run<<<157, 64>>>(h_d)... | #include <hip/hip_runtime.h>
#include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
hipMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
hipMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z3runPf
.globl _Z3runPf
.p2align 8
.type _Z3runPf,@function
_Z3runPf:
v_lshl_add_u32 v0, s15, 6, v0
s_mov_b32 s2, exec_lo
s_delay_alu instid0(VALU_DEP_1)
v_cmpx_gt_i32_e32 0x2711, v0
s_cbranch_execz .LBB0_2
s_lo... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include <iostream>
#include <string.h>
void __global__ run(float * h)
{
int idx = blockIdx.x*64+threadIdx.x;
if (idx > 10000) return;
h[idx] += 1.3f;
}
int main(int argc, char ** argv)
{
int times = atoi(argv[1]);
float * h_d;
hipMalloc(&h_d, 10000*sizeof(float));
for (int i = 0; i < times... | .text
.file "main.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z18__device_stub__runPf # -- Begin function _Z18__device_stub__runPf
.p2align 4, 0x90
.type _Z... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z3runPf
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R2, SR_CTAID.X ; /* 0x0000000000027919 */
/* 0x000e280000002500 */
/*0020*/ S2R R3... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z3runPf
.globl _Z3runPf
.p2align 8
.type _Z3runPf,@function
_Z3runPf:
v_lshl_add_u32 v0, s15, 6, v0
s_mov_b32 s2, exec_lo
s_delay_alu instid0(VALU_DEP_1)
v_cmpx_gt_i32_e32 0x2711, v0
s_cbranch_execz .LBB0_2
s_lo... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_00189640_00000000-6_main.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3672:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnreg... | .text
.file "main.hip"
# Start of file scope inline assembly
.globl _ZSt21ios_base_library_initv
# End of file scope inline assembly
.globl _Z18__device_stub__runPf # -- Begin function _Z18__device_stub__runPf
.p2align 4, 0x90
.type _Z... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} | code for sm_80
Function : kernel
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R5, SR_CTAID.X ; /* 0x0000000000057919 */
/* 0x000e220000002500 */
/*0020*/ HFMA2.MM... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} | .file "tmpxft_00192687_00000000-6_kernel.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2029:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
.... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} | #include <hip/hip_runtime.h>
#include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected kernel
.globl kernel
.p2align 8
.type kernel,@function
kernel:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x1c
s_load_b64 s[0:1], s[0:1], 0x0
s_waitcnt lgkmcnt(0)
s_and_b32 s2, s2, 0xffff
s_delay_alu instid0(SALU_CY... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include "includes.h"
// CUDA runtime
// helper functions and utilities to work with CUDA
extern "C"
__global__ void kernel(int* data, int size)
{
int id = blockDim.x * blockIdx.x + threadIdx.x;
data[id] = id;
} | .text
.file "kernel.hip"
.globl __device_stub__kernel # -- Begin function __device_stub__kernel
.p2align 4, 0x90
.type __device_stub__kernel,@function
__device_stub__kernel: # @__device_stub__kernel
.cfi_startproc
# %bb.0:
subq $88, %rsp
.cfi_def_cfa_offset 96
movq %rdi, 56(%rsp)
movl %esi, 4... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : kernel
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R5, SR_CTAID.X ; /* 0x0000000000057919 */
/* 0x000e220000002500 */
/*0020*/ HFMA2.MM... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected kernel
.globl kernel
.p2align 8
.type kernel,@function
kernel:
s_clause 0x1
s_load_b32 s2, s[0:1], 0x1c
s_load_b64 s[0:1], s[0:1], 0x0
s_waitcnt lgkmcnt(0)
s_and_b32 s2, s2, 0xffff
s_delay_alu instid0(SALU_CY... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_00192687_00000000-6_kernel.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2029:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
.... | .text
.file "kernel.hip"
.globl __device_stub__kernel # -- Begin function __device_stub__kernel
.p2align 4, 0x90
.type __device_stub__kernel,@function
__device_stub__kernel: # @__device_stub__kernel
.cfi_startproc
# %bb.0:
subq $88, %rsp
.cfi_def_cfa_offset 96
movq %rdi, 56(%rsp)
movl %esi, 4... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m; ix++)
{
idx = iy*m + ix;
B[... | code for sm_80 |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m; ix++)
{
idx = iy*m + ix;
B[... | .file "tmpxft_0014976a_00000000-6_host.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2063:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
.cf... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m; ix++)
{
idx = iy*m + ix;
B[... | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m... | .text
.p2alignl 7, 3214868480
.fill 96, 4, 3214868480
.type __hip_cuid_,@object
.section .bss,"aw",@nobits
.globl __hip_cuid_
__hip_cuid_:
.byte 0
.size __hip_cuid_, 1
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.3.2 25012 e5bf7... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <sys/time.h>
#define P (1 << 14)
double cpuSecond()
{
struct timeval tp;
gettimeofday(&tp,NULL);
return (double) tp.tv_sec + (double)tp.tv_usec*1e-6;
}
void copymat_host_x(int m, int n, int* A, int *B)
{
int ix,iy,idx;
for(iy = 0; iy < n; iy++)
for(ix = 0; ix < m... | .text
.file "host.hip"
.section .rodata.cst8,"aM",@progbits,8
.p2align 3, 0x0 # -- Begin function _Z9cpuSecondv
.LCPI0_0:
.quad 0x3eb0c6f7a0b5ed8d # double 9.9999999999999995E-7
.text
.globl _Z9cpuSecondv
.p2align 4, 0x90
.type _Z9cpuSecondv,@function
_Z9cpuSecondv: ... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80 | .text
.p2alignl 7, 3214868480
.fill 96, 4, 3214868480
.type __hip_cuid_,@object
.section .bss,"aw",@nobits
.globl __hip_cuid_
__hip_cuid_:
.byte 0
.size __hip_cuid_, 1
.ident "AMD clang version 18.0.0git (https://github.com/RadeonOpenCompute/llvm-project roc-6.3.2 25012 e5bf7... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_0014976a_00000000-6_host.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2063:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
.cf... | .text
.file "host.hip"
.section .rodata.cst8,"aM",@progbits,8
.p2align 3, 0x0 # -- Begin function _Z9cpuSecondv
.LCPI0_0:
.quad 0x3eb0c6f7a0b5ed8d # double 9.9999999999999995E-7
.text
.globl _Z9cpuSecondv
.p2align 4, 0x90
.type _Z9cpuSecondv,@function
_Z9cpuSecondv: ... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <cuda.h>
#include <cuda_runtime.h>
#define CHECK(call) { const cudaError_t error = call; if (error != cudaSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, cudaGetErrorString(error)); exit(1); }}
__global__... | code for sm_80
Function : _Z20compute_displacementPfS_S_iii
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R6, SR_CTAID.X ; /* 0x0000000000067919 */
/* 0x000e220000... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <cuda.h>
#include <cuda_runtime.h>
#define CHECK(call) { const cudaError_t error = call; if (error != cudaSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, cudaGetErrorString(error)); exit(1); }}
__global__... | .file "tmpxft_000850ea_00000000-6_projection_r.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, ... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <cuda.h>
#include <cuda_runtime.h>
#define CHECK(call) { const cudaError_t error = call; if (error != cudaSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, cudaGetErrorString(error)); exit(1); }}
__global__... | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <hip/hip_runtime.h>
#define CHECK(call) { const hipError_t error = call; if (error != hipSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, hipGetErrorString(error)); exit(1); }}
__global__ void compute_disp... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <hip/hip_runtime.h>
#define CHECK(call) { const hipError_t error = call; if (error != hipSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, hipGetErrorString(error)); exit(1); }}
__global__ void compute_disp... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z20compute_displacementPfS_S_iii
.globl _Z20compute_displacementPfS_S_iii
.p2align 8
.type _Z20compute_displacementPfS_S_iii,@function
_Z20compute_displacementPfS_S_iii:
s_clause 0x2
s_load_b32 s4, s[0:1], 0x34
s_load_b64 s[2:3], s[0:1], 0x18
s_load_b... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <hip/hip_runtime.h>
#define CHECK(call) { const hipError_t error = call; if (error != hipSuccess) { printf("Error: %s:%d, ", __FILE__, __LINE__); printf("code:%d, reason: %s\n", error, hipGetErrorString(error)); exit(1); }}
__global__ void compute_disp... | .text
.file "projection_r.hip"
.globl _Z35__device_stub__compute_displacementPfS_S_iii # -- Begin function _Z35__device_stub__compute_displacementPfS_S_iii
.p2align 4, 0x90
.type _Z35__device_stub__compute_displacementPfS_S_iii,@function
_Z35__device_stub__compute_displacementPfS_S_iii: # @_Z35__device_stub__compute_di... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z20compute_displacementPfS_S_iii
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R6, SR_CTAID.X ; /* 0x0000000000067919 */
/* 0x000e220000... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z20compute_displacementPfS_S_iii
.globl _Z20compute_displacementPfS_S_iii
.p2align 8
.type _Z20compute_displacementPfS_S_iii,@function
_Z20compute_displacementPfS_S_iii:
s_clause 0x2
s_load_b32 s4, s[0:1], 0x34
s_load_b64 s[2:3], s[0:1], 0x18
s_load_b... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_000850ea_00000000-6_projection_r.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, ... | .text
.file "projection_r.hip"
.globl _Z35__device_stub__compute_displacementPfS_S_iii # -- Begin function _Z35__device_stub__compute_displacementPfS_S_iii
.p2align 4, 0x90
.type _Z35__device_stub__compute_displacementPfS_S_iii,@function
_Z35__device_stub__compute_displacementPfS_S_iii: # @_Z35__device_stub__compute_di... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include <cuda.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * z_re * z_im... | code for sm_80
Function : _Z12mandelKernelPiffffiim
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R5, SR_CTAID.X ; /* 0x0000000000057919 */
/* 0x000e220000002500 *... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include <cuda.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * z_re * z_im... | .file "tmpxft_00047da1_00000000-6_kernel2.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include <cuda.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * z_re * z_im... | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * ... |
You are a helpful coding assistant specialized in converting HIP source code to AMD device assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * ... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z12mandelKernelPiffffiim
.globl _Z12mandelKernelPiffffiim
.p2align 8
.type _Z12mandelKernelPiffffiim,@function
_Z12mandelKernelPiffffiim:
s_clause 0x1
s_load_b32 s3, s[0:1], 0x34
s_load_b32 s2, s[0:1], 0x1c
v_and_b32_e32 v2, 0x3ff, v0
v_bfe_u3... |
You are a helpful coding assistant specialized in converting HIP source code to AMD host assembly. | #include <hip/hip_runtime.h>
#include <stdio.h>
#include <stdlib.h>
/*
__global__ static inline int mandel(float c_re, float c_im, int count)
{
float z_re = c_re, z_im = c_im;
int i;
for (i = 0; i < count; ++i)
{
if (z_re * z_re + z_im * z_im > 4.f)
break;
float new_re = z_re * z_re - z_im * z_im;
float new_im = 2.f * ... | .text
.file "kernel2.hip"
.globl _Z27__device_stub__mandelKernelPiffffiim # -- Begin function _Z27__device_stub__mandelKernelPiffffiim
.p2align 4, 0x90
.type _Z27__device_stub__mandelKernelPiffffiim,@function
_Z27__device_stub__mandelKernelPiffffiim: # @_Z27__device_stub__mandelKernelPiffffiim
.cfi_startproc
# %bb.0:
s... |
You are a helpful coding assistant specialized in converting from CUDA device assembly to AMD device assembly. | code for sm_80
Function : _Z12mandelKernelPiffffiim
.headerflags @"EF_CUDA_TEXMODE_UNIFIED EF_CUDA_64BIT_ADDRESS EF_CUDA_SM80 EF_CUDA_VIRTUAL_SM(EF_CUDA_SM80)"
/*0000*/ MOV R1, c[0x0][0x28] ; /* 0x00000a0000017a02 */
/* 0x000fe40000000f00 */
/*0010*/ S2R R5, SR_CTAID.X ; /* 0x0000000000057919 */
/* 0x000e220000002500 *... | .text
.amdgcn_target "amdgcn-amd-amdhsa--gfx1100"
.protected _Z12mandelKernelPiffffiim
.globl _Z12mandelKernelPiffffiim
.p2align 8
.type _Z12mandelKernelPiffffiim,@function
_Z12mandelKernelPiffffiim:
s_clause 0x1
s_load_b32 s3, s[0:1], 0x34
s_load_b32 s2, s[0:1], 0x1c
v_and_b32_e32 v2, 0x3ff, v0
v_bfe_u3... |
You are a helpful coding assistant specialized in converting from CUDA host assembly to AMD host assembly. | .file "tmpxft_00047da1_00000000-6_kernel2.cudafe1.cpp"
.text
#APP
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB2060:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaUnregisterFatBinary@PLT
addq $8, %rsp
... | .text
.file "kernel2.hip"
.globl _Z27__device_stub__mandelKernelPiffffiim # -- Begin function _Z27__device_stub__mandelKernelPiffffiim
.p2align 4, 0x90
.type _Z27__device_stub__mandelKernelPiffffiim,@function
_Z27__device_stub__mandelKernelPiffffiim: # @_Z27__device_stub__mandelKernelPiffffiim
.cfi_startproc
# %bb.0:
s... |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA device assembly. | #include<stdio.h>
#include<iostream>
#include<cuda.h>
int main(int argc, char* argv[]){
if(argc!=3){
std::cout<<"Usage: "<<argv[0]<<" Numblocks BlockDim\n";
return 0;
}
int nBlocks= atoi(argv[1]);
int bDim = atoi(argv[2]);
if(bDim>1024){
std::cout<<"BlockDim should be less than or equal to 1024\n";
return 0;
}
std::co... | code for sm_80 |
You are a helpful coding assistant specialized in converting CUDA source code to CUDA host assembly. | #include<stdio.h>
#include<iostream>
#include<cuda.h>
int main(int argc, char* argv[]){
if(argc!=3){
std::cout<<"Usage: "<<argv[0]<<" Numblocks BlockDim\n";
return 0;
}
int nBlocks= atoi(argv[1]);
int bDim = atoi(argv[2]);
if(bDim>1024){
std::cout<<"BlockDim should be less than or equal to 1024\n";
return 0;
}
std::co... | .file "tmpxft_0007504c_00000000-6_example1.cudafe1.cpp"
.text
#APP
.globl _ZSt21ios_base_library_initv
#NO_APP
.type _ZL26__cudaUnregisterBinaryUtilv, @function
_ZL26__cudaUnregisterBinaryUtilv:
.LFB3672:
.cfi_startproc
endbr64
subq $8, %rsp
.cfi_def_cfa_offset 16
movq _ZL20__cudaFatCubinHandle(%rip), %rdi
call __cudaU... |
You are a helpful coding assistant specialized in converting CUDA source code to HIP/AMD source code. | #include<stdio.h>
#include<iostream>
#include<cuda.h>
int main(int argc, char* argv[]){
if(argc!=3){
std::cout<<"Usage: "<<argv[0]<<" Numblocks BlockDim\n";
return 0;
}
int nBlocks= atoi(argv[1]);
int bDim = atoi(argv[2]);
if(bDim>1024){
std::cout<<"BlockDim should be less than or equal to 1024\n";
return 0;
}
std::co... | #include<stdio.h>
#include<iostream>
#include<hip/hip_runtime.h>
int main(int argc, char* argv[]){
if(argc!=3){
std::cout<<"Usage: "<<argv[0]<<" Numblocks BlockDim\n";
return 0;
}
int nBlocks= atoi(argv[1]);
int bDim = atoi(argv[2]);
if(bDim>1024){
std::cout<<"BlockDim should be less than or equal to 1024\n";
return 0... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.