diff options
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp | 24 |
1 files changed, 12 insertions, 12 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp b/src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp index 02d9486cc6..bb86d9e41d 100644 --- a/src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp +++ b/src/core/NEON/kernels/arm_gemm/interleave_indirect.cpp @@ -292,21 +292,21 @@ void Interleave(TOut *out, const TIn *in, size_t in_stride, const unsigned int y /* AArch32 */ #ifdef __arm__ /* FP32 */ -/* NEON implementation (height 6) */ +/* Neon implementation (height 6) */ template void IndirectInterleave<6, 1, VLType::None>(float *, const float * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<6, 1, VLType::None>(float *, const float *, size_t, const convolver<float> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<6, 1, VLType::None>(float *, const float *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); /* FP16 */ #if __ARM_FP16_ARGS -/* NEON implementation using FP32 kernel (height 6) */ +/* Neon implementation using FP32 kernel (height 6) */ template void IndirectInterleave<6, 1, VLType::None>(float *, const __fp16 * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<6, 1, VLType::None>(float *, const __fp16 *, size_t, const convolver<__fp16> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<6, 1, VLType::None>(float *, const __fp16 *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); #endif /* __ARM_FP16_ARGS */ /* BF16 */ -/* NEON implementation using FP32 kernel */ +/* Neon implementation using FP32 kernel */ template void IndirectInterleave<6, 1, VLType::None>(float *, const bfloat16 * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<6, 1, VLType::None>(float *, const bfloat16 *, size_t, const convolver<bfloat16> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<6, 1, VLType::None>(float *, const bfloat16 *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -315,7 +315,7 @@ template void Interleave<6, 1, VLType::None>(float *, const bfloat16 *, size_t, /* AArch64 */ #ifdef __aarch64__ /* FP32 */ -/* NEON/SVE implementation (height 8) */ +/* Neon/SVE implementation (height 8) */ template void IndirectInterleave<8, 1, VLType::None>(float *, const float * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<8, 1, VLType::None>(float *, const float *, size_t, const convolver<float> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 1, VLType::None>(float *, const float *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -339,7 +339,7 @@ template void ConvolutionInterleave<8, 1, VLType::None>(float *, const __fp16 *, template void Interleave<8, 1, VLType::None>(float *, const __fp16 *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); /* BF16 */ -/* NEON/SVE BFDOT */ +/* Neon/SVE BFDOT */ #ifdef V8P6_BF template void IndirectInterleave<8, 2, VLType::None>(bfloat16 *, const bfloat16 * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<8, 2, VLType::None>(bfloat16 *, const bfloat16 *, size_t, const convolver<bfloat16> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -350,7 +350,7 @@ template void ConvolutionInterleave<8, 4, VLType::None>(bfloat16 *, const bfloat template void Interleave<8, 4, VLType::None>(bfloat16 *, const bfloat16 *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); #endif // V8P6_BF -/* NEON/SVE using FP32 kernel */ +/* Neon/SVE using FP32 kernel */ template void IndirectInterleave<8, 1, VLType::None>(float *, const bfloat16 * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<8, 1, VLType::None>(float *, const bfloat16 *, size_t, const convolver<bfloat16> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 1, VLType::None>(float *, const bfloat16 *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -365,12 +365,12 @@ template void ConvolutionInterleave<8, 1, VLType::None>(uint16_t *, const uint16 template void Interleave<8, 1, VLType::None>(uint16_t *, const uint16_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); /* INT8 */ -/* NEON SMLA/SMLAL (height 4, block 16) */ +/* Neon SMLA/SMLAL (height 4, block 16) */ template void IndirectInterleave<4, 16, VLType::None>(int8_t *, const int8_t * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<4, 16, VLType::None>(int8_t *, const int8_t *, size_t, const convolver<int8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<4, 16, VLType::None>(int8_t *, const int8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); -/* NEON SDOT (height 8, block 4) */ +/* Neon SDOT (height 8, block 4) */ template void IndirectInterleave<8, 4, VLType::None>(int8_t *, const int8_t * const * const *, unsigned int, unsigned int, unsigned int y0, unsigned int ymax, unsigned int k0, unsigned int kmax, bool, int32_t); template void ConvolutionInterleave<8, 4, VLType::None>(int8_t *, const int8_t *, size_t, const convolver<int8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 4, VLType::None>(int8_t *, const int8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -382,17 +382,17 @@ template void ConvolutionInterleave<8, 8, VLType::None>(int8_t *, const int8_t * template void Interleave<8, 8, VLType::None>(int8_t *, const int8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); #endif // MMLA_INT8 -/* NEON SDOT (height 8, block 1) */ +/* Neon SDOT (height 8, block 1) */ template void IndirectInterleave<8, 1, VLType::None>(int16_t *, const int8_t * const * const *, unsigned int, unsigned int, unsigned int y0, unsigned int ymax, unsigned int k0, unsigned int kmax, bool, int32_t); template void ConvolutionInterleave<8, 1, VLType::None>(int16_t *, const int8_t *, size_t, const convolver<int8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 1, VLType::None>(int16_t *, const int8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); -/* NEON SMLA/SMLAL (height 4, block 16) */ +/* Neon SMLA/SMLAL (height 4, block 16) */ template void IndirectInterleave<4, 16, VLType::None>(uint8_t *, const uint8_t * const * const *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void ConvolutionInterleave<4, 16, VLType::None>(uint8_t *, const uint8_t *, size_t, const convolver<uint8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<4, 16, VLType::None>(uint8_t *, const uint8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); -/* NEON SDOT (height 8, block 4) */ +/* Neon SDOT (height 8, block 4) */ template void IndirectInterleave<8, 4, VLType::None>(uint8_t *, const uint8_t * const * const *, unsigned int, unsigned int, unsigned int y0, unsigned int ymax, unsigned int k0, unsigned int kmax, bool, int32_t); template void ConvolutionInterleave<8, 4, VLType::None>(uint8_t *, const uint8_t *, size_t, const convolver<uint8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 4, VLType::None>(uint8_t *, const uint8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); @@ -404,7 +404,7 @@ template void ConvolutionInterleave<8, 8, VLType::None>(uint8_t *, const uint8_t template void Interleave<8, 8, VLType::None>(uint8_t *, const uint8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); #endif // MMLA_INT8 -/* NEON 16-bit (height 8, block 1) */ +/* Neon 16-bit (height 8, block 1) */ template void IndirectInterleave<8, 1, VLType::None>(uint16_t *, const uint8_t * const * const *, unsigned int, unsigned int, unsigned int y0, unsigned int ymax, unsigned int k0, unsigned int kmax, bool, int32_t); template void ConvolutionInterleave<8, 1, VLType::None>(uint16_t *, const uint8_t *, size_t, const convolver<uint8_t> &, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); template void Interleave<8, 1, VLType::None>(uint16_t *, const uint8_t *, size_t, unsigned int, unsigned int, unsigned int, unsigned int, bool, int32_t); |