Searched refs:FastInterleavedAndBiasedNumericArrayConverter (Results 1 – 3 of 3) sorted by relevance
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/cutlass_extensions/ |
| H A D | interleaved_numeric_conversion.h | 50 struct FastInterleavedAndBiasedNumericArrayConverter { struct
54 struct FastInterleavedAndBiasedNumericArrayConverter<half_t, uint8_t, 4> {
88 struct FastInterleavedAndBiasedNumericArrayConverter<half_t, uint8_t, N> {
100 … FastInterleavedAndBiasedNumericArrayConverter<scalar_result_type, scalar_source_type, VEC_WIDTH>
126 struct FastInterleavedAndBiasedNumericArrayConverter<bfloat16_t, uint8_t, 4> {
178 struct FastInterleavedAndBiasedNumericArrayConverter<bfloat16_t, uint8_t, N> {
190 … FastInterleavedAndBiasedNumericArrayConverter<scalar_result_type, scalar_source_type, VEC_WIDTH>
216 struct FastInterleavedAndBiasedNumericArrayConverter<half_t, uint4b_t, 8> {
290 struct FastInterleavedAndBiasedNumericArrayConverter<half_t, uint4b_t, N> {
302 … FastInterleavedAndBiasedNumericArrayConverter<scalar_result_type, scalar_source_type, VEC_WIDTH>
[all …]
|
| /aosp_15_r20/external/pytorch/aten/src/ATen/native/cuda/cutlass_extensions/gemm/threadblock/ |
| H A D | default_dq_mma.h | 33 … FastInterleavedAndBiasedNumericArrayConverter<typename MmaOperator::ArchMmaOperator::ElementB,
54 … FastInterleavedAndBiasedNumericArrayConverter<typename MmaOperator::ArchMmaOperator::ElementB,
|
| H A D | default_dq_mma_multistage.h | 152 using Converter = FastInterleavedAndBiasedNumericArrayConverter<ElementA,
322 using Converter = FastInterleavedAndBiasedNumericArrayConverter<ElementA,
|