CUTLASS 3.5.0 (#1411)

This commit is contained in:
Vijay Thakkar
2024-03-19 17:51:04 -04:00
committed by GitHub
parent ffa34e7075
commit 629f4653c3
468 changed files with 48729 additions and 7252 deletions
+3 -3
View File
@@ -117,8 +117,8 @@ public:
void run() {
/// Device memory containing output
cutlass::device_memory::allocation< ArrayTy > output(kThreads);
std::vector< ArrayTy > output_host(kThreads);
cutlass::device_memory::allocation< ArrayTy > output(static_cast<size_t>(kThreads));
std::vector< ArrayTy > output_host(static_cast<size_t>(kThreads));
dim3 grid(1,1);
dim3 block(kThreads, 1, 1);
@@ -138,7 +138,7 @@ public:
ASSERT_EQ(result, cudaSuccess) << "CUDA error: " << cudaGetErrorString(result);
char const *ptr_host = reinterpret_cast<char const *>(output_host.data());
for (int i = 0; i < sizeof(ArrayTy) * kThreads; ++i) {
for (size_t i = 0; i < sizeof(ArrayTy) * kThreads; ++i) {
EXPECT_FALSE(ptr_host[i]);
}