Add s8f32 kernels and dynamic QuantizationInfo

- Add support for QASYMM_SIGNED*QASYMM8_SIGNED->F32 in
  CpuGemmLowpMatrixMultiplyCore
- Add s8f32 kernel using existing s8->s32 kernels with a new
  DequantizeFloat OutputStage, the structure is similar to Requantize32
  but the opposite way around.
- Add SME s8f32 kernels with integrated support for DequantizeFloat.
- Add scale to CpuGemmLowpOffsetContributionKernel.
- Add virtual dequantize scale to gemm_common, only implemented for
  gemm_interleaved.
- Update year to 2024 in generate_build_files.
- Add dynamic flag to QuantizationInfo which signals to operators that
  it can change after configuration
- Add support for dynamic quantization in NEGEMMLowpMatrixMultiplyCore
- Add dynamic quantization fixture by extending
  GEMMLowpGenericMatrixMultiplyCoreValidationFixture
- Add GEMMLowpDequantizedMatrixMultiplyValidationFixture
- Store k (number of cols of A) rather than k_offset in the offset
  contribution kernels so that we can recompute it when the other
  offsets change

relates to: ONCPUML-1444 MLINFSW-439

Co-authored-by: Milos Puzovic <Milos.Puzovic@arm.com>
Co-authored-by: David Mansell <David.Mansell@arm.com>
Change-Id: I58a3acf2c09289a303e52eea6b336a696a5bc8da
Signed-off-by: Jonathan Deakin <jonathan.deakin@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11022
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 8 insertions, 7 deletions

diff --git a/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h
index 824c4443ad..6d07675d3d 100644
--- a/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h
+++ b/arm_compute/runtime/NEON/functions/NEGEMMLowpMatrixMultiplyCore.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2021, 2023 Arm Limited.
+ * Copyright (c) 2017-2021, 2023-2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCORE_H
-#define ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCORE_H
+#ifndef ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NEGEMMLOWPMATRIXMULTIPLYCORE_H
+#define ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NEGEMMLOWPMATRIXMULTIPLYCORE_H
 
 #include "arm_compute/core/Types.h"
 #include "arm_compute/function_info/GEMMInfo.h"
@@ -80,6 +80,7 @@ public:
      * |QASYMM8_SIGNED |QASYMM8_SIGNED     |S32      |S32            |
      * |QASYMM8_SIGNED |QSYMM8_PER_CHANNEL |S32      |S32            |
      * |QASYMM8_SIGNED |QSYMM8             |S32      |S32            |
+     * |QASYMM8_SIGNED |QASYMM8_SIGNED     |F32      |F32            |
      *
      * @note GEMM_LOWP:  low precision GEMM kernel
      *  This kernel performs the following computations:
@@ -88,12 +89,12 @@ public:
      *  -# Convert b values from QASYMM8 to int32 add b_offset to each of them.
      *  -# Compute the matrix product of the resulting a * b in int32.
      *
-     * @note The @p output type is S32 if @p gemm_info.type == GEMMLowpOutputStageType::NONE. It is QASYMM8/QASYMM8_SIGNED otherwise
+     * @note The @p output type is S32 if @p gemm_info.type == GEMMLowpOutputStageType::NONE. It is QASYMM8/QASYMM8_SIGNED/F32 otherwise
      *
      * @param[in]  a         First input tensor  (Matrix A). Data type supported: QASYMM8/QASYMM8_SIGNED.
      * @param[in]  b         Second input tensor (Matrix B). Data type supported: QASYMM8/QASYMM8_SIGNED/QSYMM8/QSYMM8_PER_CHANNEL.
-     * @param[in]  c         Third input tensor  (Matrix C). It can be a nullptr. Data type supported: S32
-     * @param[out] output    Output tensor. Data type supported: Data type supported: S32/QASYMM8/QASYMM8_SIGNED
+     * @param[in]  c         Third input tensor  (Matrix C). It can be a nullptr. Data type supported: S32/F32
+     * @param[out] output    Output tensor. Data type supported: Data type supported: S32/QASYMM8/QASYMM8_SIGNED/F32
      * @param[in]  gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and
      *                       if the reshape of matrix B should be executed only for the first run
      */
@@ -120,4 +121,4 @@ private:
     std::unique_ptr<Impl> _impl;
 };
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_NEGEMMLOWPMATRIXMULTIPLYCORE_H */
+#endif // ACL_ARM_COMPUTE_RUNTIME_NEON_FUNCTIONS_NEGEMMLOWPMATRIXMULTIPLYCORE_H