GitHub-Proxy/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-08-12 03:39:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add unit test for -Tensor<complex> on GPU

Browse Source
This commit is contained in:
Gael Guennebaud 2018-07-12 17:19:38 +02:00
parent 12e1ebb68b
commit 44ea5f7623
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
unsupported/test/cxx11_tensor_complex_cwise_ops_gpu.cu
View File

@ -48,11 +48,13 @@ void test_cuda_complex_cwise_ops() {
Add = 0, Add = 0,
Sub, Sub,
Mul, Mul,
Div Div,
Neg,
NbOps
}; };
Tensor<std::complex<T>, 1, 0, int> actual(kNumItems); Tensor<std::complex<T>, 1, 0, int> actual(kNumItems);
for (int op = Add; op <= Div; op++) { for (int op = Add; op < NbOps; op++) {
std::complex<T> expected; std::complex<T> expected;
switch (static_cast<CwiseOp>(op)) { switch (static_cast<CwiseOp>(op)) {
case Add: case Add:
@ -71,6 +73,10 @@ void test_cuda_complex_cwise_ops() {
gpu_out.device(gpu_device) = gpu_in1 / gpu_in2; gpu_out.device(gpu_device) = gpu_in1 / gpu_in2;
expected = a / b; expected = a / b;
break; break;
case Neg:
gpu_out.device(gpu_device) = -gpu_in1;
expected = -a;
break;
} }
assert(cudaMemcpyAsync(actual.data(), d_out, complex_bytes, cudaMemcpyDeviceToHost, assert(cudaMemcpyAsync(actual.data(), d_out, complex_bytes, cudaMemcpyDeviceToHost,
gpu_device.stream()) == cudaSuccess); gpu_device.stream()) == cudaSuccess);