diff options
| author | Michael Tyler <michael.tyler@arm.com> | 2024-06-04 15:47:37 +0100 |
|---|---|---|
| committer | Michael Tyler <michael.tyler@arm.com> | 2024-06-25 09:10:13 +0000 |
| commit | fc94f4d23abd4bc427b701f54ad85282e9ec7872 (patch) | |
| tree | 5e2980599256e2b2f4374e5beb61596fc95c9d5a /src/core/NEON/kernels/arm_gemm/quantized.cpp | |
| parent | c2237ec4094c7824f8f7e61bc89504d01c5b59ff (diff) | |
| download | ComputeLibrary-fc94f4d23abd4bc427b701f54ad85282e9ec7872.tar.gz | |
Update CPU kernels and add mixed sign GEMM support
- Add support for mixed sign quantized convolution.
- Add support for mixed sign dequantized GEMM.
- Add SME FP16 GEMV kernel.
- Change SME vector length function to use RDSVL instead of static variable.
- Add GEMM dilation support internally (not exposed yet).
- Remove unused "get_default_activation_values" functions.
- Add SVE fixed format interleaved BF16 DOT kernel.
- Updates and optimizations to assembly kernels.
Resolves COMPMID-6926
Change-Id: I227f502502611d4cc4111c89e30c53ce94079544
Signed-off-by: Michael Tyler <michael.tyler@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11570
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/quantized.cpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/quantized.cpp | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/quantized.cpp b/src/core/NEON/kernels/arm_gemm/quantized.cpp index 6da9f4be0e..f24d5956e5 100644 --- a/src/core/NEON/kernels/arm_gemm/quantized.cpp +++ b/src/core/NEON/kernels/arm_gemm/quantized.cpp @@ -745,6 +745,10 @@ template void requantize_block_32(const Requantize32 &qp, unsigned int width, un const uint32_t *input, unsigned int in_stride, uint8_t *output, unsigned int out_stride, const int32_t *row_bias, const int32_t *col_bias, unsigned int start_col); +template void requantize_block_32(const Requantize32 &qp, unsigned int width, unsigned int height, + const int32_t *input, unsigned int in_stride, uint8_t *output, unsigned int out_stride, + const int32_t *row_bias, const int32_t *col_bias, unsigned int start_col); + /* * Routine (and helpers) to compute row sums needed for offset correction. * |