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/cpu/operators/CpuConv2d.h | |
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/cpu/operators/CpuConv2d.h')
-rw-r--r-- | src/cpu/operators/CpuConv2d.h | 13 |
1 files changed, 10 insertions, 3 deletions
diff --git a/src/cpu/operators/CpuConv2d.h b/src/cpu/operators/CpuConv2d.h index 71b9e15dc1..0012ff6609 100644 --- a/src/cpu/operators/CpuConv2d.h +++ b/src/cpu/operators/CpuConv2d.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2021, 2023 Arm Limited. + * Copyright (c) 2017-2021, 2023-2024 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -21,6 +21,10 @@ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ + +#ifndef ACL_SRC_CPU_OPERATORS_CPUCONV2D_H +#define ACL_SRC_CPU_OPERATORS_CPUCONV2D_H + #include "arm_compute/function_info/ActivationLayerInfo.h" #include "src/core/common/Macros.h" @@ -81,6 +85,7 @@ public: * |F16 |F16 |F16 |F16 | * |F32 |F32 |F32 |F32 | * |QASYMM8 |QASYMM8 |S32 |QASYMM8 | + * |QASYMM8 |QASYMM8_SIGNED |S32 |QASYMM8 | * |QASYMM8 |QSYMM8_PER_CHANNEL |S32 |QASYMM8 | * |QASYMM8_SIGNED |QASYMM8_SIGNED |S32 |QASYMM8_SIGNED | * |QASYMM8_SIGNED |QSYMM8_PER_CHANNEL |S32 |QASYMM8_SIGNED | @@ -89,7 +94,7 @@ public: * while every optional dimension from 4 and above represent a batch of inputs. * Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. * @param[in] weights Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. - * Data type supported: Same as @p src, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED. + * Data type supported: Same as @p src, also could be QSYMM8_PER_CHANNEL or QASYMM8_SIGNED if input is QASYMM8/QASYMM8_SIGNED. * @param[in] biases Biases tensor info. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. * Data type supported: Same as @p src, except for input of QASYMM8/QASYMM8_SIGNED type where biases should be of S32 type. * @param[out] dst Destination tensor info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. @@ -135,7 +140,7 @@ public: * while every optional dimension from 4 and above represent a batch of inputs. * Data types supported: QASYMM8/QASYMM8_SIGNED/F16/F32. * @param[in] weights Weights tensor info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. - * Data type supported:Same as @p src, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED. + * Data type supported:Same as @p src, also could be QSYMM8_PER_CHANNEL or QASYMM8_SIGNED if input is QASYMM8/QASYMM8_SIGNED. * @param[in] dst Destination tensor info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs. * Data types supported: Same as @p src. * @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo. @@ -167,3 +172,5 @@ private: }; } // namespace cpu } // namespace arm_compute + +#endif // ACL_SRC_CPU_OPERATORS_CPUCONV2D_H |