TomSang
bfc2f4516a
1. Simply enable test on NV
Some need minor fix
performance/compute/hipPerfDotProduct.cpp
performance/dispatch/hipPerfDispatchSpeed.cpp
performance/memory/hipPerfBufferCopyRectSpeed.cpp
performance/memory/hipPerfBufferCopySpeed.cpp
performance/memory/hipPerfDevMemReadSpeed.cpp
performance/memory/hipPerfDevMemWriteSpeed.cpp
performance/memory/hipPerfMemcpy.cpp
performance/memory/hipPerfMemset.cpp
performance/memory/hipPerfSharedMemReadSpeed.cpp
performance/stream/hipPerfDeviceConcurrency.cpp
performance/stream/hipPerfStreamCreateCopyDestroy.cpp
2. Enable and fix on NV
performance/compute/hipPerfMandelbrot.cpp
Root cause: coordIdx is random
Solution: Initialize coordIdx correctly
performance/memory/hipPerfMemFill.cpp
Root cause: Hip ext Apis called.
Solution: Exclude case with Hip ext Apis involved
performance/memory/hipPerfMemMallocCpyFree.cpp
Root cause: Test allocates device memory more than GPU has.
Solution: Allocate device memory in terms of GPU capacity.
tests/performance/memory/hipPerfSampleRate.cpp
Root cause: Cuda has no operators += for float2 and float4.
Solution: Provide the operators.
performance/stream/hipPerfStreamConcurrency.cpp
Root cause:float4 format doesn't match cude.
operators are missing in cuda lib.
Solution: Use (x, y, z, w) format.
Add necessary float4 operatoris for cuda.
Change-Id: I5add29ebabcfb21fb3ef89d09004c5d13423a291
115 righe
3.2 KiB
C++
115 righe
3.2 KiB
C++
/*
|
|
Copyright (c) 2015 - 2021 Advanced Micro Devices, Inc. All rights reserved.
|
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
of this software and associated documentation files (the "Software"), to deal
|
|
in the Software without restriction, including without limitation the rights
|
|
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
copies of the Software, and to permit persons to whom the Software is
|
|
furnished to do so, subject to the following conditions:
|
|
The above copyright notice and this permission notice shall be included in
|
|
all copies or substantial portions of the Software.
|
|
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
THE SOFTWARE.
|
|
*/
|
|
|
|
/* HIT_START
|
|
* BUILD: %t %s ../../src/test_common.cpp
|
|
* TEST: %t
|
|
* HIT_END
|
|
*/
|
|
|
|
#include "test_common.h"
|
|
#include <iostream>
|
|
#include <chrono>
|
|
|
|
#define NUM_SIZE 8
|
|
#define NUM_ITER 0x40000
|
|
|
|
|
|
using namespace std;
|
|
|
|
class hipPerfMemcpy {
|
|
private:
|
|
unsigned int numBuffers_;
|
|
size_t totalSizes_[NUM_SIZE];
|
|
void setHostBuffer(int *A, int val, size_t size);
|
|
public:
|
|
hipPerfMemcpy();
|
|
~hipPerfMemcpy() {};
|
|
void open(int deviceID);
|
|
void run(unsigned int testNumber);
|
|
};
|
|
|
|
hipPerfMemcpy::hipPerfMemcpy() : numBuffers_(0) {
|
|
for (int i = 0; i < NUM_SIZE; i++) {
|
|
totalSizes_[i] = 1 << (i + 6);
|
|
}
|
|
};
|
|
|
|
void hipPerfMemcpy::setHostBuffer(int *A, int val, size_t size) {
|
|
size_t len = size / sizeof(int);
|
|
for (int i = 0; i < len; i++) {
|
|
A[i] = val;
|
|
}
|
|
}
|
|
|
|
void hipPerfMemcpy::open(int deviceId) {
|
|
int nGpu = 0;
|
|
HIPCHECK(hipGetDeviceCount(&nGpu));
|
|
if (nGpu < 1) {
|
|
failed("No GPU!");
|
|
}
|
|
|
|
HIPCHECK(hipSetDevice(deviceId));
|
|
hipDeviceProp_t props = {0};
|
|
HIPCHECK(hipGetDeviceProperties(&props, deviceId));
|
|
std::cout << "info: running on bus " << "0x" << props.pciBusID << " " << props.name
|
|
<< " with " << props.multiProcessorCount << " CUs" << " and device id: " << deviceId << std::endl;
|
|
}
|
|
|
|
void hipPerfMemcpy::run(unsigned int testNumber) {
|
|
int *A, *Ad;
|
|
A = new int[totalSizes_[testNumber]];
|
|
setHostBuffer(A, 1, totalSizes_[testNumber]);
|
|
hipMalloc(&Ad, totalSizes_[testNumber]);
|
|
|
|
auto start = chrono::steady_clock::now();
|
|
|
|
for (int j = 0; j < NUM_ITER; j++) {
|
|
hipMemcpy(Ad, A, totalSizes_[testNumber], hipMemcpyHostToDevice);
|
|
}
|
|
|
|
hipDeviceSynchronize();
|
|
|
|
auto end = chrono::steady_clock::now();
|
|
chrono::duration<double, micro> diff = end - start;
|
|
|
|
cout << "hipPerfMemcpy[" << testNumber << "] " << "Host to Device copy took "
|
|
<< diff.count() / NUM_ITER << " us for memory size of " << totalSizes_[testNumber]
|
|
<< " Bytes" << endl;
|
|
|
|
delete [] A;
|
|
HIPCHECK(hipFree(Ad));
|
|
|
|
}
|
|
|
|
|
|
int main() {
|
|
hipPerfMemcpy hipPerfMemcpy;
|
|
|
|
int deviceId = 0;
|
|
hipPerfMemcpy.open(deviceId);
|
|
|
|
for (auto testCase = 0; testCase < NUM_SIZE; testCase++) {
|
|
hipPerfMemcpy.run(testCase);
|
|
}
|
|
|
|
passed();
|
|
|
|
}
|