-
Notifications
You must be signed in to change notification settings - Fork 982
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add couple configs into generator.py for mixed input MM
- Loading branch information
1 parent
ffa34e7
commit e130f14
Showing
17 changed files
with
1,279 additions
and
28 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
97 changes: 97 additions & 0 deletions
97
test/unit/gemm/device/gemm_universal_bf16t_s8n_f32t_mixed_input_tensor_op_f32_sm80.cu
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| /*************************************************************************************************** | ||
| * Copyright (c) 2023 - 2024 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. | ||
| * | ||
| **************************************************************************************************/ | ||
| /*! \file | ||
| \brief Tests for device-wide GEMM interface | ||
| */ | ||
|
|
||
| #include <iostream> | ||
|
|
||
| #include "../../common/cutlass_unit_test.h" | ||
| #include "cutlass/cutlass.h" | ||
|
|
||
| #include "cutlass/gemm/device/gemm_universal.h" | ||
|
|
||
| #include "cutlass/util/host_tensor.h" | ||
| #include "cutlass/util/reference/host/gemm.h" | ||
| #include "cutlass/util/reference/host/tensor_compare.h" | ||
| #include "cutlass/util/reference/host/tensor_copy.h" | ||
| #include "cutlass/util/reference/host/tensor_fill.h" | ||
| #include "cutlass/util/tensor_view_io.h" | ||
|
|
||
| #include "testbed_universal.h" | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
| #if defined(CUTLASS_ARCH_MMA_SM80_SUPPORTED) | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
|
|
||
| TEST(SM80_Device_GemmUniversal_bf16t_s8n_f32t_mixed_input_tensor_op_f32, 128x128x64_64x64x64) { | ||
|
|
||
| using ElementA = cutlass::bfloat16_t; | ||
| using ElementB = int8_t; | ||
| using ElementOutput = float; | ||
| using ElementAccumulator = float; | ||
|
|
||
| using Gemm = cutlass::gemm::device::GemmUniversal< | ||
| ElementA, | ||
| cutlass::layout::RowMajor, | ||
| ElementB, | ||
| cutlass::layout::ColumnMajor, | ||
| ElementOutput, | ||
| cutlass::layout::RowMajor, | ||
| ElementAccumulator, | ||
| cutlass::arch::OpClassTensorOp, | ||
| cutlass::arch::Sm80, | ||
| cutlass::gemm::GemmShape<128, 128, 64>, | ||
| cutlass::gemm::GemmShape<64, 64, 64>, | ||
| cutlass::gemm::GemmShape<16, 8, 16>, | ||
| cutlass::epilogue::thread::LinearCombination< | ||
| ElementOutput, 128 / cutlass::sizeof_bits<ElementOutput>::value, | ||
| ElementAccumulator, ElementAccumulator>, | ||
| cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle<>, | ||
| 4, // Stages | ||
| 8, // AlignmentA | ||
| 16, // AlignmentB | ||
| cutlass::arch::OpMultiplyAddMixedInputUpcast, | ||
| cutlass::ComplexTransform::kNone, | ||
| cutlass::ComplexTransform::kNone | ||
| >; | ||
|
|
||
| EXPECT_TRUE(test::gemm::device::TestAllGemmUniversal<Gemm>()); | ||
| } | ||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
| #endif // #if defined(CUTLASS_ARCH_MMA_SM80_SUPPORTED) | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// |
97 changes: 97 additions & 0 deletions
97
test/unit/gemm/device/gemm_universal_bf16t_u8n_f32t_mixed_input_tensor_op_f32_sm80.cu
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,97 @@ | ||
| /*************************************************************************************************** | ||
| * Copyright (c) 2023 - 2024 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. | ||
| * | ||
| **************************************************************************************************/ | ||
| /*! \file | ||
| \brief Tests for device-wide GEMM interface | ||
| */ | ||
|
|
||
| #include <iostream> | ||
|
|
||
| #include "../../common/cutlass_unit_test.h" | ||
| #include "cutlass/cutlass.h" | ||
|
|
||
| #include "cutlass/gemm/device/gemm_universal.h" | ||
|
|
||
| #include "cutlass/util/host_tensor.h" | ||
| #include "cutlass/util/reference/host/gemm.h" | ||
| #include "cutlass/util/reference/host/tensor_compare.h" | ||
| #include "cutlass/util/reference/host/tensor_copy.h" | ||
| #include "cutlass/util/reference/host/tensor_fill.h" | ||
| #include "cutlass/util/tensor_view_io.h" | ||
|
|
||
| #include "testbed_universal.h" | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
| #if defined(CUTLASS_ARCH_MMA_SM80_SUPPORTED) | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
|
|
||
| TEST(SM80_Device_GemmUniversal_bf16t_u8n_f32t_mixed_input_tensor_op_f32, 128x128x64_64x64x64) { | ||
|
|
||
| using ElementA = cutlass::bfloat16_t; | ||
| using ElementB = uint8_t; | ||
| using ElementOutput = float; | ||
| using ElementAccumulator = float; | ||
|
|
||
| using Gemm = cutlass::gemm::device::GemmUniversal< | ||
| ElementA, | ||
| cutlass::layout::RowMajor, | ||
| ElementB, | ||
| cutlass::layout::ColumnMajor, | ||
| ElementOutput, | ||
| cutlass::layout::RowMajor, | ||
| ElementAccumulator, | ||
| cutlass::arch::OpClassTensorOp, | ||
| cutlass::arch::Sm80, | ||
| cutlass::gemm::GemmShape<128, 128, 64>, | ||
| cutlass::gemm::GemmShape<64, 64, 64>, | ||
| cutlass::gemm::GemmShape<16, 8, 16>, | ||
| cutlass::epilogue::thread::LinearCombination< | ||
| ElementOutput, 128 / cutlass::sizeof_bits<ElementOutput>::value, | ||
| ElementAccumulator, ElementAccumulator>, | ||
| cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle<>, | ||
| 4, // Stages | ||
| 8, // AlignmentA | ||
| 16, // AlignmentB | ||
| cutlass::arch::OpMultiplyAddMixedInputUpcast, | ||
| cutlass::ComplexTransform::kNone, | ||
| cutlass::ComplexTransform::kNone | ||
| >; | ||
|
|
||
| EXPECT_TRUE(test::gemm::device::TestAllGemmUniversal<Gemm>()); | ||
| } | ||
| //////////////////////////////////////////////////////////////////////////////// | ||
|
|
||
| #endif // #if defined(CUTLASS_ARCH_MMA_SM80_SUPPORTED) | ||
|
|
||
| //////////////////////////////////////////////////////////////////////////////// |
Oops, something went wrong.