diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-06-27 17:00:52 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-07-26 11:55:15 +0000 |
| commit | cfa2bba98169cb5ab1945462514be1b6badf7d98 (patch) | |
| tree | 1635e6e9463e9798c7195f0aa71b5df3f2650df1 /src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp | |
| parent | f59b16f42ef68bde877b70816ffb953d64c8baa3 (diff) | |
| download | ComputeLibrary-cfa2bba98169cb5ab1945462514be1b6badf7d98.tar.gz | |
COMPMID-2178: Update GEMM assembly code.
Perform offset reduction and requantization within the assembly wrapper.
Change-Id: I5d5b3e1f6f9ef4c71805362c57f88ff199c027a3
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1541
Comments-Addressed: Pablo Marquez <pablo.tello@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp')
| -rw-r--r-- | src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp b/src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp index 5b70c8724c..aa40113c5e 100644 --- a/src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp +++ b/src/runtime/NEON/functions/NEGEMMLowpAssemblyMatrixMultiplyCore.cpp @@ -43,7 +43,7 @@ NEGEMMLowpAssemblyMatrixMultiplyCore::NEGEMMLowpAssemblyMatrixMultiplyCore(std:: { } -void NEGEMMLowpAssemblyMatrixMultiplyCore::configure(const ITensor *a, const ITensor *b, ITensor *output) +void NEGEMMLowpAssemblyMatrixMultiplyCore::configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *output) { ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(a, 1, DataType::U8, DataType::S8); ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(output, 1, DataType::U32, DataType::S32); @@ -59,7 +59,7 @@ void NEGEMMLowpAssemblyMatrixMultiplyCore::configure(const ITensor *a, const ITe case DataType::QASYMM8: case DataType::U8: { - _asm_glue.configure(a, b, output, 1.f, 0.f, GEMMInfo(false, false, true)); + _asm_glue.configure(a, b, c, output, 1.f, 0.f, GEMMInfo(false, false, true)); run_optimised = _asm_glue.is_configured(); break; } |