mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
Add optimized blockwise gemm using ck wrapper (#1157)
* Add optimized blockwise gemm using ck wrapper * Add basic gemm example * Update docs * Add tutorial for gemm using ck wrapper * Add perf note * edits * Fix cmake * Fixes --------- Co-authored-by: Lisa Delaney <lisa.delaney@amd.com>
This commit is contained in:
@@ -172,10 +172,10 @@ __host__ __device__ constexpr auto GenerateUpperDims(const Tuple<Transforms...>&
|
||||
}
|
||||
}
|
||||
|
||||
template <typename... Ts, typename Shape, typename FlattenDescriptor>
|
||||
template <typename... Ts, typename Shape, typename UnrolledDescriptor>
|
||||
__host__ __device__ constexpr auto GenerateSlicedDescriptor(const Tuple<Ts...>& idx,
|
||||
const Shape& shape,
|
||||
const FlattenDescriptor& flatten_desc)
|
||||
const UnrolledDescriptor& flatten_desc)
|
||||
{
|
||||
constexpr auto old_shape_dims = decltype(UnrollNestedTuple(shape))::Size();
|
||||
|
||||
|
||||
Reference in New Issue
Block a user