ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 20:40:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge commit 'b60af5bde965a2bb007bb582f7836b43ca647b81' into develop

Browse Source
This commit is contained in:
assistant-librarian[bot]
2025-09-30 16:14:10 +00:00
parent 631a25de61
commit ee9718a427
115 changed files with 2849 additions and 756 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
test/magic_number_division/magic_number_division.cpp
View File

@@ -56,10 +56,27 @@ __host__ void cpu_magic_number_division(uint32_t magic_multiplier,
}
}
int main(int, char*[])
int main(int argc, char* argv[])
{
uint64_t num_divisor = 4096;
uint64_t num_dividend = 1L << 16;
uint64_t num_divisor = 4096;
uint64_t num_dividend = 1L << 16;
uint32_t divisor_start = 0;
uint32_t divisor_end = num_divisor;
if(argc == 1)
{
// use default range
}
else if(argc == 3)
{
divisor_start = std::stoi(argv[1]);
divisor_end = std::stoi(argv[2]);
}
else
{
std::cerr << "arg1 to 2: divisor_start divisor_end" << std::endl;
return 1;
}
std::vector<int32_t> divisors_host(num_divisor);
std::vector<int32_t> dividends_host(num_dividend);
@@ -90,6 +107,10 @@ int main(int, char*[])
for(std::size_t i = 0; i < num_divisor; ++i)
{
if(i < divisor_start || i > divisor_end)
{
continue;
}
// run naive division on GPU
gpu_naive_division<<<1024, 256>>>(
divisors_host[i],