Support for Group GEMM in CUTLASS Profiler for Geforce and Spark (#3092)
Co-authored-by: dePaul Miller <23461061+depaulmillz@users.noreply.github.com>
This commit is contained in:
co-authored by
dePaul Miller
parent
e5fcd125a5
commit
73c59c055c
@@ -46,7 +46,7 @@ set(TEST_SMALL_LARGE_GROUP --m=128 --n=128 --groups=50 --iterations=0)
|
||||
set(TEST_RANDOM_PERF --iterations=10) # Random problem sizes
|
||||
set(TEST_RANDOM_PERF_LARGE_GROUP --groups=50 --iterations=10) # Random problem sizes
|
||||
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|121a")
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|120f|121a")
|
||||
cutlass_example_add_executable(
|
||||
79a_blackwell_geforce_nvfp4_bf16_gemm
|
||||
79a_blackwell_geforce_nvfp4_bf16_gemm.cu
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|121a")
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|120f|121a")
|
||||
cutlass_example_add_executable(
|
||||
80a_blackwell_geforce_mxfp8_bf16_sparse_gemm
|
||||
80a_blackwell_geforce_mxfp8_bf16_sparse_gemm.cu
|
||||
|
||||
@@ -28,7 +28,7 @@
|
||||
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|121a")
|
||||
if (CUTLASS_NVCC_ARCHS MATCHES "120a|120f|121a")
|
||||
cutlass_example_add_executable(
|
||||
87a_blackwell_geforce_fp8_bf16_gemm_blockwise
|
||||
87a_blackwell_geforce_fp8_bf16_gemm_blockwise.cu
|
||||
|
||||
Reference in New Issue
Block a user