[arm_gemm] Import fixed-format kernels from gemm_linux.
This is a No Functional Change Intended (NFCI) patch. It imports the
kernel in the code, but the interface to select them and expose the
format of the weight tensors to the user will be provided in a
subsequent patch.
Kernels and kernel selection code in arm_gemm has been provided
by David.Mansell <David.Mansell@arm.com>.
The kernels are not compiled in the library by default, but need to be
selected via the `scons` option `experimental_fixed_format_kernels=1`.
Resolves: ONCPUML-829
Signed-off-by: Francesco.Petrogalli@arm.com <francesco.petrogalli@arm.com>
Change-Id: If00ccb2b9b7221e01b214cf9783111226ccc8bf4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7380
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/filelist.json b/filelist.json
index dc4be05..681cacd 100644
--- a/filelist.json
+++ b/filelist.json
@@ -1421,7 +1421,7 @@
},
"Gemm": {
"deps": [ "Quantize", "Add"],
- "files": {
+ "files": {
"common": [
"src/cpu/kernels/CpuConvertQuantizedSignednessKernel.cpp",
"src/cpu/kernels/CpuGemmMatrixAdditionKernel.cpp",
@@ -1540,6 +1540,16 @@
],
"estate64": [
"src/core/NEON/kernels/arm_gemm/kernels/a64_sgemv_pretransposed/generic.cpp"
+ ],
+ "experimental_fixed_format_kernels": [
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_bf16fp32_mmla_6x16/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp16_mla_6x32/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32_mla_6x16/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffhybrid_fp32bf16fp32_mmla_4x24/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_bf16fp32_dot_8x12/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_bf16fp32_mmla_8x12/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_fp16_mla_8x24/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/a64_ffinterleaved_fp32_mla_8x12/generic.cpp"
]
},
"sve": {
@@ -1584,7 +1594,20 @@
"src/core/NEON/kernels/arm_gemm/kernels/sve_smallK_hybrid_u8u32_dot_8x1VL/generic.cpp",
"src/core/NEON/kernels/arm_gemm/mergeresults-sve.cpp",
"src/core/NEON/kernels/arm_gemm/transform-sve.cpp"
- ]
+ ],
+ "experimental_fixed_format_kernels": [
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_bf16fp32_mmla_6x4VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_fp16_mla_6x4VL/a64fx.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_fp16_mla_6x4VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_fp32_mla_6x4VL/a64fx.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_fp32_mla_6x4VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffhybrid_fp32bf16fp32_mmla_4x6VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffinterleaved_bf16fp32_mmla_8x3VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffinterleaved_fp16_mla_8x3VL/a64fx.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffinterleaved_fp16_mla_8x3VL/generic.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffinterleaved_fp32_mla_8x3VL/a64fx.cpp",
+ "src/core/NEON/kernels/arm_gemm/kernels/sve_ffinterleaved_fp32_mla_8x3VL/generic.cpp"
+ ]
}
}
},