CUTLASS 3.8 Release (#2059)

* CUTLASS 3.8 Release

* update

* Update README.md

* Revert "Update README.md"

This reverts commit b353e36fe83e0815f99b44e46c0c95494c44726b.

* update

* update

---------

Co-authored-by: Haicheng Wu <57973641+hwu36@users.noreply.github.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
This commit is contained in:
mihir-awatramani
2025-01-25 02:44:06 -05:00
committed by GitHub
co-authored by Haicheng Wu Haicheng Wu
parent 9eb01fa0b0
commit 389e493055
290 changed files with 91222 additions and 291 deletions
+39
View File
@@ -48,3 +48,42 @@
////////////////////////////////////////////////////////////////////////////////////////////////////
#if (defined(CUTLASS_ARCH_MMA_SM100A_ENABLED))
# define CUTE_ARCH_TMA_SM90_ENABLED
# define CUTE_ARCH_DEVICE_MODIFIABLE_TMA_SM90_ENABLED
# define CUTE_ARCH_STSM_SM90_ENABLED
#endif
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
# define CUTE_ARCH_TCGEN05_TF32_MMA_ENABLED
# define CUTE_ARCH_TCGEN05_F16F32_MMA_ENABLED
# define CUTE_ARCH_TCGEN05_MXF8F6F4_MMA_ENABLED
# define CUTE_ARCH_TCGEN05_MXF4_MMA_ENABLED
# define CUTE_ARCH_TCGEN05_MXF4NVF4_MMA_ENABLED
#endif
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
# define CUTE_ARCH_TCGEN05_S8_MMA_ENABLED
#endif
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
# define CUTE_ARCH_LDSM_SM100A_ENABLED
# define CUTE_ARCH_STSM_SM100A_ENABLED
#endif
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
# define CUTE_ARCH_TCGEN05_TMEM_ENABLED
#endif
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
# define CUTE_ARCH_TMA_SM100_ENABLED
#endif
// {add, mul, fma}.f32x2 PTX
#if defined(CUTLASS_ARCH_MMA_SM100A_ENABLED)
#define CUTE_ARCH_FLOAT2_MATH_ENABLED
#endif