Add SM80/89 blockwise scaling kernel, support FP8 block/groupwise on Ada, INT8 on Ampere

examples/85_ada_ampere_gemm_with_blockwise_scaling/CMakeLists.txt

@@ -0,0 +1,48 @@
+
+# Copyright (c) 2024 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: BSD-3-Clause
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+# 1. Redistributions of source code must retain the above copyright notice, this
+# list of conditions and the following disclaimer.
+#
+# 2. Redistributions in binary form must reproduce the above copyright notice,
+# this list of conditions and the following disclaimer in the documentation
+# and/or other materials provided with the distribution.
+#
+# 3. Neither the name of the copyright holder nor the names of its
+# contributors may be used to endorse or promote products derived from
+# this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+cutlass_example_add_executable(
+  85a_ada_fp8_gemm_with_groupwise_scaling_cute
+  85a_ada_fp8_gemm_with_groupwise_scaling_cute.cu
+  )
+
+cutlass_example_add_executable(
+  85b_ada_fp8_gemm_with_blockwise_scaling_cute
+  85b_ada_fp8_gemm_with_blockwise_scaling_cute.cu
+  )
+
+cutlass_example_add_executable(
+  85c_ampere_int8_gemm_with_groupwise_scaling_cute
+  85c_ampere_int8_gemm_with_groupwise_scaling_cute.cu
+  )
+
+cutlass_example_add_executable(
+  85d_ampere_int8_gemm_with_blockwise_scaling_cute
+  85d_ampere_int8_gemm_with_blockwise_scaling_cute.cu
+  )

examples/CMakeLists.txt

@@ -163,6 +163,7 @@ foreach(EXAMPLE
   82_blackwell_distributed_gemm
   83_blackwell_sparse_gemm
   84_blackwell_narrow_precision_sparse_gemm
+  85_ada_ampere_gemm_with_blockwise_scaling
   )
 
   add_subdirectory(${EXAMPLE})

include/cutlass/gemm/collective/collective_mma.hpp

@@ -37,6 +37,7 @@
 
 #include "cutlass/gemm/collective/sm70_mma_twostage.hpp"
 #include "cutlass/gemm/collective/sm80_mma_multistage.hpp"
+#include "cutlass/gemm/collective/sm80_mma_multistage_blockwise_scaling.hpp"
 #include "cutlass/gemm/collective/sm90_mma_multistage_gmma_ss_warpspecialized.hpp"
 #include "cutlass/gemm/collective/sm90_mma_multistage_gmma_rs_warpspecialized.hpp"
 #include "cutlass/gemm/collective/sm90_mma_tma_gmma_ss.hpp"