Remove hip-hcc codes: Part three
1.Rename include/hip/hcc_detail/ as include/hip/amd_detail/ 2.Rename include/hip/nvcc_detail/ as include/hip/nvidia_detail/ 3.Create __HIP_PLATFORM_AMD__ to replace __HIP_PLATFORM_HCC__ 4.Create __HIP_PLATFORM_NVIDIA__ to replace __HIP_PLATFORM_NVCC__ After hcc_detail, nvcc_detail, __HIP_PLATFORM_HCC__ and __HIP_PLATFORM_NVCC__ have been removed from upstream, they will be removed from hip runtime. Change-Id: I1ae457effd739d6c25bca203c1724b026be21fce
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# bit_extract
|
||||
|
||||
Show an application written directly in HIP which uses platform-specific check on __HIP_PLATFORM_HCC__ to enable use of
|
||||
Show an application written directly in HIP which uses platform-specific check on __HIP_PLATFORM_AMD__ to enable use of
|
||||
an instruction that only exists on the HCC platform.
|
||||
|
||||
See related [blog](http://gpuopen.com/platform-aware-coding-inside-hip/) demonstrating platform specialization.
|
||||
|
||||
@@ -39,9 +39,9 @@ __global__ void bit_extract_kernel(uint32_t* C_d, const uint32_t* A_d, size_t N)
|
||||
size_t stride = hipBlockDim_x * hipGridDim_x;
|
||||
|
||||
for (size_t i = offset; i < N; i += stride) {
|
||||
#ifdef __HIP_PLATFORM_HCC__
|
||||
#ifdef __HIP_PLATFORM_AMD__
|
||||
C_d[i] = __bitextract_u32(A_d[i], 8, 4);
|
||||
#else /* defined __HIP_PLATFORM_NVCC__ or other path */
|
||||
#else /* defined __HIP_PLATFORM_NVIDIA__ or other path */
|
||||
C_d[i] = ((A_d[i] & 0xf00) >> 8);
|
||||
#endif
|
||||
}
|
||||
|
||||
@@ -26,7 +26,7 @@ THE SOFTWARE.
|
||||
#include <fstream>
|
||||
#include <vector>
|
||||
|
||||
#ifdef __HIP_PLATFORM_HCC__
|
||||
#ifdef __HIP_PLATFORM_AMD__
|
||||
#include <hip/hip_ext.h>
|
||||
#endif
|
||||
|
||||
|
||||
@@ -57,7 +57,7 @@ int main(int argc, char* argv[]) {
|
||||
hipDeviceProp_t props;
|
||||
CHECK(hipGetDeviceProperties(&props, device /*deviceID*/));
|
||||
printf("info: running on device %s\n", props.name);
|
||||
#ifdef __HIP_PLATFORM_HCC__
|
||||
#ifdef __HIP_PLATFORM_AMD__
|
||||
printf("info: architecture on AMD GPU device is: %s\n", props.gcnArchName);
|
||||
#endif
|
||||
printf("info: allocate host mem (%6.2f MB)\n", 2 * Nbytes / 1024.0 / 1024.0);
|
||||
|
||||
Reference in New Issue
Block a user