diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2023-04-13 18:22:58 +0100 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2023-04-17 15:54:44 +0000 |
| commit | 9d0c4deb760efc2ca07e5e0b8218995201ad8a1f (patch) | |
| tree | 8f64b754d05768e2f69cfae387137140a6bb22b5 /src/gpu/cl/ClKernelLibrary.cpp | |
| parent | 99145f787e9e99b45522f16d861c8527583f2b4e (diff) | |
| download | ComputeLibrary-9d0c4deb760efc2ca07e5e0b8218995201ad8a1f.tar.gz | |
Add quantized CL MatMul kernels for Lhs NT/T, Rhs NT
Implement OpenCL kernels for batched Matrix Multiplication for the quantized data types QASYMM8 and QASYMM8_SIGNED.
Quantized MatMul is supported with the following MatMul attributes:
* adj_x = false, adj_y = false
* adj_x = true, adj_y = false
We consider native format kernels only. In other words, no reshaping of the operand matrices is done.
Resolves: COMPMID-5921, COMPMID-5922
Change-Id: I99e0f68054a2bd635c60ec2641acc2e7ff398473
Signed-off-by: Omar Al Khatib <omar.alkhatib@arm.com>
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9435
Reviewed-by: SiCong Li <sicong.li@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/ClKernelLibrary.cpp')
| -rw-r--r-- | src/gpu/cl/ClKernelLibrary.cpp | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/src/gpu/cl/ClKernelLibrary.cpp b/src/gpu/cl/ClKernelLibrary.cpp index 44b086f2fc..e657687887 100644 --- a/src/gpu/cl/ClKernelLibrary.cpp +++ b/src/gpu/cl/ClKernelLibrary.cpp @@ -323,6 +323,8 @@ const std::map<std::string, std::string> ClKernelLibrary::_kernel_program_map = { "mat_mul_native_nt_t", "common/mat_mul.cl" }, { "mat_mul_native_t_nt", "common/mat_mul.cl" }, { "mat_mul_native_t_t", "common/mat_mul.cl" }, + { "mat_mul_native_quantized_nt_nt", "common/mat_mul_quantized.cl" }, + { "mat_mul_native_quantized_t_nt", "common/mat_mul_quantized.cl" }, { "max_unpooling_layer_2", "common/unpooling_layer.cl" }, { "mean_stddev_normalization", "common/mean_stddev_normalization.cl" }, { "memset", "common/memset.cl" }, @@ -794,6 +796,10 @@ const std::map<std::string, std::string> ClKernelLibrary::_program_source_map = "common/mat_mul.cl", #include "./cl_kernels/common/mat_mul.clembed" }, + { + "common/mat_mul_quantized.cl", +#include "./cl_kernels/common/mat_mul_quantized.clembed" + }, #ifdef ENABLE_NCHW_KERNELS { "nchw/batch_to_space.cl", |