CUTLASS 3.2.1 (#1113)

* Updates for 3.2.1 release.

* Minor fix in gemm op profiler for raster order.

* Add scheduler mapping for raster order in the kernels.
This commit is contained in:
ANIKET SHIVAM
2023-09-26 17:24:26 -04:00
committed by GitHub
parent e0aaa3c3b3
commit 90d3b0fb18
428 changed files with 22252 additions and 21761 deletions
@@ -291,6 +291,7 @@ struct GemmUniversalArguments {
// Needed for some 3.x kernels
int sm_count;
library::RasterOrder raster_order;
};
/////////////////////////////////////////////////////////////////////////////////////////////////
@@ -250,6 +250,13 @@ enum class EpilogueKind {
kInvalid
};
enum class RasterOrder {
kAlongN,
kAlongM,
kHeuristic,
kInvalid
};
/////////////////////////////////////////////////////////////////////////////////////////////////
} // namespace library
@@ -170,6 +170,13 @@ char const *to_string(ConvKind type, bool pretty = false);
template <>
ConvKind from_string<ConvKind>(std::string const &str);
/// Converts a RasterOrder enumerant to a string
char const *to_string(RasterOrder type, bool pretty = false);
/// Convers a RasterOrder enumerant from a string
template<>
RasterOrder from_string<RasterOrder>(std::string const &str);
/// Lexical cast from int64_t to string
std::string lexical_cast(int64_t int_value);