fb335f6a5f
CUTLASS 2.0 Substantially refactored for - Better performance, particularly for native Turing Tensor Cores - Robust and durable templates spanning the design space - Encapsulated functionality embodying modern C++11 programming techniques - Optimized containers and data types for efficient, generic, portable device code Updates to: - Quick start guide - Documentation - Utilities - CUTLASS Profiler Native Turing Tensor Cores - Efficient GEMM kernels targeting Turing Tensor Cores - Mixed-precision floating point, 8-bit integer, 4-bit integer, and binarized operands Coverage of existing CUTLASS functionality: - GEMM kernels targeting CUDA and Tensor Cores in NVIDIA GPUs - Volta Tensor Cores through native mma.sync and through WMMA API - Optimizations such as parallel reductions, threadblock rasterization, and intra-threadblock reductions - Batched GEMM operations - Complex-valued GEMMs Note: this commit and all that follow require a host compiler supporting C++11 or greater.
222 lines
8.3 KiB
Plaintext
222 lines
8.3 KiB
Plaintext
/***************************************************************************************************
|
|
* Copyright (c) 2017-2019, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without modification, are permitted
|
|
* provided that the following conditions are met:
|
|
* * Redistributions of source code must retain the above copyright notice, this list of
|
|
* conditions and the following disclaimer.
|
|
* * 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.
|
|
* * Neither the name of the NVIDIA CORPORATION 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 NVIDIA CORPORATION 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 TOR (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 unit tests for matrix_coord
|
|
*/
|
|
|
|
#include "../common/cutlass_unit_test.h"
|
|
|
|
#include "cutlass/matrix_coord.h"
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
namespace test {
|
|
namespace core {
|
|
|
|
void test_matrix_coord(cutlass::MatrixCoord::Index row, cutlass::MatrixCoord::Index column) {
|
|
cutlass::MatrixCoord matrix_coord(row, column);
|
|
|
|
EXPECT_EQ(matrix_coord.row(), row);
|
|
EXPECT_EQ(matrix_coord.column(), column);
|
|
}
|
|
|
|
void test_matrix_coord_operator_addition() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
auto matrix_coord_c = matrix_coord_a + matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_c.row(), row_a + row_b);
|
|
EXPECT_EQ(matrix_coord_c.column(), column_a + column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_subtraction() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
auto matrix_coord_c = matrix_coord_a - matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_c.row(), row_a - row_b);
|
|
EXPECT_EQ(matrix_coord_c.column(), column_a - column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_multiply() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
auto matrix_coord_c = matrix_coord_a * matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_c.row(), row_a * row_b);
|
|
EXPECT_EQ(matrix_coord_c.column(), column_a * column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_division() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
auto matrix_coord_c = matrix_coord_a / matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_c.row(), row_a / row_b);
|
|
EXPECT_EQ(matrix_coord_c.column(), column_a / column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_addition_assignment() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
matrix_coord_a += matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_a.row(), row_a + row_b);
|
|
EXPECT_EQ(matrix_coord_a.column(), column_a + column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_subtraction_assignment() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
matrix_coord_a -= matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_a.row(), row_a - row_b);
|
|
EXPECT_EQ(matrix_coord_a.column(), column_a - column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_multiply_assignment() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
matrix_coord_a *= matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_a.row(), row_a * row_b);
|
|
EXPECT_EQ(matrix_coord_a.column(), column_a * column_b);
|
|
}
|
|
|
|
void test_matrix_coord_operator_division_assignment() {
|
|
cutlass::MatrixCoord::Index row_a = 13;
|
|
cutlass::MatrixCoord::Index column_a = 42;
|
|
cutlass::MatrixCoord::Index row_b = 20;
|
|
cutlass::MatrixCoord::Index column_b = 15;
|
|
|
|
cutlass::MatrixCoord matrix_coord_a(row_a, column_a);
|
|
cutlass::MatrixCoord matrix_coord_b(row_b, column_b);
|
|
|
|
matrix_coord_a /= matrix_coord_b;
|
|
|
|
EXPECT_EQ(matrix_coord_a.row(), row_a / row_b);
|
|
EXPECT_EQ(matrix_coord_a.column(), column_a / column_b);
|
|
}
|
|
}
|
|
} // namespace test
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_row12_column24) {
|
|
cutlass::MatrixCoord::Index row = 12;
|
|
cutlass::MatrixCoord::Index column = 24;
|
|
test::core::test_matrix_coord(row, column);
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_addition) {
|
|
test::core::test_matrix_coord_operator_addition();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_subtraction) {
|
|
test::core::test_matrix_coord_operator_subtraction();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_multiply) {
|
|
test::core::test_matrix_coord_operator_multiply();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_division) {
|
|
test::core::test_matrix_coord_operator_division();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_addition_assignment) {
|
|
test::core::test_matrix_coord_operator_addition_assignment();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_subtraction_assignment) {
|
|
test::core::test_matrix_coord_operator_subtraction_assignment();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_multiply_assignment) {
|
|
test::core::test_matrix_coord_operator_multiply_assignment();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|
|
|
|
TEST(Matrix_Coord, basic_operator_division_assignment) {
|
|
test::core::test_matrix_coord_operator_division_assignment();
|
|
}
|
|
|
|
/////////////////////////////////////////////////////////////////////////////////////////////////
|