Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use enum for vendor ID #166

Open
wants to merge 3 commits into
base: develop
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -201,16 +201,16 @@ VkFFTResult sample_0_benchmark_VkFFT_single(VkGPU* vkGPU, uint64_t file_output,
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)(((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize);
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -213,16 +213,16 @@ VkFFTResult sample_1000_benchmark_VkFFT_single_2_4096(VkGPU* vkGPU, uint64_t fil
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -216,16 +216,16 @@ VkFFTResult sample_1001_benchmark_VkFFT_double_2_4096(VkGPU* vkGPU, uint64_t fil
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -215,16 +215,16 @@ VkFFTResult sample_1002_benchmark_VkFFT_half_2_4096(VkGPU* vkGPU, uint64_t file_
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -212,16 +212,16 @@ VkFFTResult sample_1003_benchmark_VkFFT_single_3d_2_512(VkGPU* vkGPU, uint64_t f
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -216,16 +216,16 @@ VkFFTResult sample_1004_benchmark_VkFFT_quadDoubleDouble_2_4096(VkGPU* vkGPU, ui
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -239,16 +239,16 @@ VkFFTResult sample_100_benchmark_VkFFT_single_nd_dct(VkGPU* vkGPU, uint64_t file
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -240,16 +240,16 @@ VkFFTResult sample_101_benchmark_VkFFT_double_nd_dct(VkGPU* vkGPU, uint64_t file
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -198,9 +198,9 @@ VkFFTResult sample_10_benchmark_VkFFT_single_multipleBuffers(VkGPU* vkGPU, uint6

//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / (numBuf * bufferSize[0]) > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / (numBuf * bufferSize[0]);
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
if (num_iter == 0) num_iter = 1;
if (vkGPU->physicalDeviceProperties.vendorID != 0x8086) num_iter *= 5;
if (vkGPU->physicalDeviceProperties.vendorID != VKFFT_VENDOR_INTEL) num_iter *= 5;
double totTime = 0;
VkFFTLaunchParams launchParams = {};
resFFT = performVulkanFFTiFFT(vkGPU, &app, &launchParams, num_iter, &totTime);
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,16 +206,16 @@ VkFFTResult sample_1_benchmark_VkFFT_double(VkGPU* vkGPU, uint64_t file_output,
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@ VkFFTResult sample_2_benchmark_VkFFT_half(VkGPU* vkGPU, uint64_t file_output, FI

//PARAMETERS THAT CAN BE ADJUSTED FOR SPECIFIC GPU's - this configuration is by no means final form
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) {
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) {
if (n > 22)//128byte coalescing has a limit of 2^24 max size
configuration.coalescedMemory = 64;
else
Expand All @@ -104,7 +104,7 @@ VkFFTResult sample_2_benchmark_VkFFT_half(VkGPU* vkGPU, uint64_t file_output, FI
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) {
if (vendorID == VKFFT_VENDOR_INTEL) {
if (n > 22)//128byte coalescing has a limit of 2^24 max size
configuration.coalescedMemory = 64;
else
Expand All @@ -114,7 +114,7 @@ VkFFTResult sample_2_benchmark_VkFFT_half(VkGPU* vkGPU, uint64_t file_output, FI
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) {
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) {
if (n > 22)//128byte coalescing has a limit of 2^24 max size
configuration.coalescedMemory = 64;
else
Expand Down Expand Up @@ -236,11 +236,11 @@ VkFFTResult sample_2_benchmark_VkFFT_half(VkGPU* vkGPU, uint64_t file_output, FI
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
if (vendorID == 0x8086) num_iter /= 4;
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==4)
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -211,16 +211,16 @@ VkFFTResult sample_3_benchmark_VkFFT_single_3d(VkGPU* vkGPU, uint64_t file_outpu
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -222,16 +222,16 @@ VkFFTResult sample_4_benchmark_VkFFT_single_3d_zeropadding(VkGPU* vkGPU, uint64_
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,16 +206,16 @@ VkFFTResult sample_5_benchmark_VkFFT_single_disableReorderFourStep(VkGPU* vkGPU,
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)3 * 4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;
double totTime = 0;
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -205,16 +205,16 @@ VkFFTResult sample_6_benchmark_VkFFT_single_r2c(VkGPU* vkGPU, uint64_t file_outp
//Submit FFT+iFFT.
uint64_t num_iter = (((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize > 1000) ? 1000 : (uint64_t)((uint64_t)4096 * 1024.0 * 1024.0) / bufferSize;
#if(VKFFT_BACKEND==0)
if (vkGPU->physicalDeviceProperties.vendorID == 0x8086) num_iter /= 4;
if (vkGPU->physicalDeviceProperties.vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;
#elif(VKFFT_BACKEND==3)
cl_uint vendorID;
clGetDeviceInfo(vkGPU->device, CL_DEVICE_VENDOR_ID, sizeof(cl_int), &vendorID, 0);
if (vendorID == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (vendorID == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#elif(VKFFT_BACKEND==4)
ze_device_properties_t device_properties;
res = zeDeviceGetProperties(vkGPU->device, &device_properties);
if (res != 0) return VKFFT_ERROR_FAILED_TO_GET_ATTRIBUTE;
if (device_properties.vendorId == 0x8086) num_iter /= 4;//smaller benchmark for Intel GPUs
if (device_properties.vendorId == VKFFT_VENDOR_INTEL) num_iter /= 4;//smaller benchmark for Intel GPUs
#endif
if (num_iter == 0) num_iter = 1;

Expand Down
Loading