- 671d1b0 QS8 4x16c4-aarch64-neondot-ld64 IGEMM microkernel by Frank Barchard · 3 years, 6 months ago
- 5655cb7 QS8 GEMM 2x8c16 MLAL PADAL assembly microkernel for AArch64 by Frank Barchard · 3 years, 6 months ago
- 4cea232 Built-in end-to-end benchmark on sparse models by Marat Dukhan · 3 years, 6 months ago
- 89e12f8 QS8 IGEMM for Cortex A55 by Frank Barchard · 3 years, 6 months ago
- 12a23bb Benchmark randomized QU8 MobileNet v1 model by Marat Dukhan · 3 years, 6 months ago
- 62b4ff7 Remove 12x8 QS8 GEMM and IGEMM Neon dotproduct microkernels. by Frank Barchard · 3 years, 6 months ago
- da78da1 QS8 C8 Neon microkernels with MUL and MLA versions. by Frank Barchard · 3 years, 6 months ago
- 4a4be4e QS8 1x16c4 ld32 GEMM microkernel using NEON dot product by Frank Barchard · 3 years, 6 months ago
- 02121ca QS8 Neon IGEMM microkernels with 8 bit MUL using DUP by Frank Barchard · 3 years, 6 months ago
- a5e242c QS8 LD32 GEMM microkernel for big cores with dotproduct by Frank Barchard · 3 years, 6 months ago
- 36f95cf QS8 Neon IGEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 6 months ago
- 71c4d1a QS8 Neon GEMM C16 microkernel with two 8 bit multiplies and vpadal to accumulate. by Frank Barchard · 3 years, 6 months ago
- a6cba1d Add A55 microkernel to QS8 E2E benchmark. by Frank Barchard · 3 years, 6 months ago
- 32389c6 QS8 e2e benchmark for C2 neon microkernels by Frank Barchard · 3 years, 6 months ago
- d79391d QS8 C8 Neon igemm by Frank Barchard · 3 years, 6 months ago
- 725a8e7 Wrap MR=1 end to end benchmarks with #if XNN_ENABLE_E2E_MR1 by Frank Barchard · 3 years, 6 months ago
- 4c032f3 E2E run benchmarks from fastest to slowest instruction set by Frank Barchard · 3 years, 6 months ago
- b8c9fa9 QS8 e2e benchmark add all x86 microkernels. by Frank Barchard · 3 years, 7 months ago
- 19f4748 QS8 e2e benchmark add all Web Assembly microkernels. by Frank Barchard · 3 years, 7 months ago
- 15c0036 QS8 e2e benchmark add all ARM microkernels. by Frank Barchard · 3 years, 7 months ago
- dc909cb qs8-gemm-e2e benchmark for comparing performance of quantized microkernels by Frank Barchard · 3 years, 7 months ago
- 8247e21 C2 QS8 microkernel using mull then mlal with KC loop of 16 by Frank Barchard · 3 years, 7 months ago
- 5899012 QS8 Neon GEMM C8 microkernel with 8 bit multiply and vpadal to accumulate. by Frank Barchard · 3 years, 7 months ago
- a93765f Add MR=1 versions of QS8 gemm benchmarks by Frank Barchard · 3 years, 7 months ago
- 2302ffd QS8 Neon GEMM microkernel with 8 bit multiply and vpadal to accumulate by Frank Barchard · 3 years, 7 months ago
- ec0bf14 QS8 GEMM and IGEMM 3x8 3x16 and IGEMM 4x8 and 4x16 by Frank Barchard · 3 years, 7 months ago
- 4ecae2e QS8 Neon GEMM microkernel with 8 bit multiply by Frank Barchard · 3 years, 7 months ago
- cfbc849 Add 4x8 and 4x16 qs8 gemm microkernels by Frank Barchard · 3 years, 7 months ago
- c5704bf WebAssembly DWConv2D 3x3 stride 2 loadsplat by Frank Barchard · 3 years, 8 months ago
- c6889b3 WebAssembly DWConv2D 5x5 stride 2 loadsplat by Frank Barchard · 3 years, 8 months ago
- 02bb429 WebAssembly DWConv2D 3x3p1 adapted from NEON by Frank Barchard · 3 years, 8 months ago
- b20dcd6 WASMSIMD dwconv2d 5x5p2 use loadsplat by Frank Barchard · 3 years, 8 months ago
- 802fcae Additional SSE/SSE2 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 9 months ago
- 412e2f4 Rename WASMSIMD dwconv2d functions to splat or loadsplat by Frank Barchard · 3 years, 9 months ago
- 3de5dfa Remove PSIMD dependency by Marat Dukhan · 3 years, 9 months ago
- c8bbe70 Benchmarks for NEON versions of DWCONV2D CHW microkernels by Marat Dukhan · 3 years, 9 months ago
- 0725b8d Rename WebAssembly SIMD source files and functions with x86 or arm suffix after wasmsimd by Frank Barchard · 3 years, 9 months ago
- 1631e3e Refactor SpMM benchmarks by Marat Dukhan · 3 years, 9 months ago
- 3a30521 Refactor accuracy evaluation benchmarks by Marat Dukhan · 3 years, 9 months ago
- 5b86c43 NEON versions of non-blocked F32 SpMM microkernels by Marat Dukhan · 3 years, 9 months ago
- 102e9ea Revert "Remove PSIMD dependency" by Marat Dukhan · 3 years, 9 months ago
- cee4e95 Remove PSIMD dependency by Marat Dukhan · 3 years, 9 months ago
- e7223ee WASMSIMD dwconv2d 5x5s2 tests and benchmark by Frank Barchard · 3 years, 9 months ago
- 4e89587 Guard microbenchmarks against running microkernels on incompatible CPUs by Marat Dukhan · 3 years, 9 months ago
- d713e8a Refactor microbenchmarks by Marat Dukhan · 3 years, 9 months ago
- ff0624e Add WebAssembly dwconv2d_chw_3x3s2p1 benchmark by Frank Barchard · 3 years, 9 months ago
- 401d97b Refactor Sigmoid operator benchmark by Marat Dukhan · 3 years, 9 months ago
- b6bd4bc Implement ELU operator by Marat Dukhan · 3 years, 9 months ago
- ed6baaf Vector ELU microkernels by Marat Dukhan · 3 years, 9 months ago
- 20a0741 Web Assemble DWConv2D f32_dwconv2d_chw_ukernel_5x5p2__wasmsimd adapted from Neon by Frank Barchard · 3 years, 9 months ago
- 2213606 xnn_f32_conv_hwc2chw_ukernel_3x3s2p1c3x4__wasmsimd_2x2 based on SSE version by Frank Barchard · 3 years, 9 months ago
- 3b80045 WAsm SIMD version of DWCONV2D CHW 3x3p1 by Frank Barchard · 3 years, 9 months ago
- db5c32d WasmSIMD dwconv2d generate x86 optimized version. by Frank Barchard · 3 years, 9 months ago
- 1a95305 Replace DWConv2D PSIMD with WAsm SIMD. by Frank Barchard · 3 years, 9 months ago
- e8bfcc8 Add output_stride argument in SpMM microkernels by Marat Dukhan · 3 years, 9 months ago
- c2c0d16 SpMM pipelined benchmark. by Frank Barchard · 3 years, 10 months ago
- beca652 Rename unroll to x for SpMM microkernels with unrolled loop by Frank Barchard · 3 years, 10 months ago
- ccca214 SSE variant of 5x5s2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 10 months ago
- d050389 SSE variants of 5x5 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 30d4b25 Auto-generate 5x5s2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 29c0c33 Auto-generate 5x5s2p2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 846c0c6 Add 32x1 32x2 32x4 SPMM microkernels and remove 4x1 4x2 4x4 for WASMSIMD, Neon and SSE by Frank Barchard · 3 years, 10 months ago
- 149f0ea Auto-generate NEON 5x5p2 DWCONV micro-kernels by Marat Dukhan · 3 years, 10 months ago
- c4efb00 Auto-generate scalar 5x5p2 DWCONV CHW micro-kernels by Marat Dukhan · 3 years, 10 months ago
- cf5b3c3 Auto-generate scalar versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 82f0c32 Auto-generate NEON/NEONFMA versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 0ff9718 Auto-generate SSE versions of DWCONV2D CHW 3x3s2p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 91249d2 Auto-generate scalar versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- c581e48 NEON versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 1268a24 Auto-generate AArch64 NEONFMA versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 98f2eeb SSSE3 versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- 470078a Auto-generate SSE versions of DWCONV2D CHW 3x3p1 micro-kernels by Marat Dukhan · 3 years, 10 months ago
- bf715f9 Rename DWCONV CHW microkernels to DWCONV2D CHW by Marat Dukhan · 3 years, 10 months ago
- 6f469a5 Minor refactoring in DWCONV CHW microkernels by Marat Dukhan · 3 years, 10 months ago
- c451e8a WAsm SpMM microkernels unrolled by 2 and 4. by Frank Barchard · 3 years, 10 months ago
- 1c6cad9 Suffix DWCONV CHW microkernels with block size by Marat Dukhan · 3 years, 10 months ago
- 7515777 Scale input width in DWCONV CHW interface by sizeof(float) by Marat Dukhan · 3 years, 10 months ago
- ae7e8b2 Remove remnants of SpCHW layout in DWCONV-CHW microkernels by Marat Dukhan · 3 years, 10 months ago
- 9e05340 Replace PSIMD SpMM microkernels with WAsm SIMD. by Frank Barchard · 3 years, 10 months ago
- c79427c Avoid batch-replication of indirection buffer in DW Conv and Avg Pooling by Marat Dukhan · 3 years, 10 months ago
- dc2b29c AVX float32 sigmoid ukernels. by T.J. Alumbaugh · 3 years, 10 months ago
- 146e999 Replace QS8 4x8 with 2x8 neon microkernel. Improves performance for aarch32. by Frank Barchard · 3 years, 11 months ago
- f2742c4 Cortex A55r1 QS8 GEMM microkernel by Frank Barchard · 3 years, 11 months ago
- 31328cb Add RUY benchmark to qs8_gemm_bench by Frank Barchard · 3 years, 11 months ago
- 0797eb1 Rename QS8 assembly GEMM kernels to ld64 by Frank Barchard · 3 years, 11 months ago
- f1fd89e 1x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 11 months ago
- 31bb45b 4x16 QS8 GEMM AARCH64 assembly microkernel using dot product. by Frank Barchard · 3 years, 11 months ago
- a48848f 4x8, 6x8 and 8x16 Neon dot product GEMM microkernels by Frank Barchard · 4 years ago
- d9ca7e6 AVX512F versions of Sigmoid microkernel by Marat Dukhan · 4 years ago
- 2fa1745 6x16 QS8 GEMM for Neon dot product by Frank Barchard · 4 years ago
- d243c1a LUT-based SSE Sigmoid microkernels by Marat Dukhan · 4 years ago
- fc2844e FP16 hardswish operator benchmark by Frank Barchard · 4 years ago
- 66f3ccd End-to-end FP16 MobileNet v3 benchmarks by Marat Dukhan · 4 years ago
- ef4ce31 Remove trailing whitespace by Marat Dukhan · 4 years ago
- 70a9618 End-to-end QS8 MobileNet v2 benchmark by Marat Dukhan · 4 years ago
- 37297a6 F32-RELU unrolled more for improved performance on Web Assembly by Frank Barchard · 4 years ago
- 9f5ccb3 f32 relu microkernel WASM assembly x2 and x4 unrolled loops by Frank Barchard · 4 years ago
- a964473 Add xnn_qs8_gemm_minmax_ukernel_${MR}x${NR}c4__neondot (ARMv8.2+dotprod). by Benoit Jacob · 4 years ago
- d91624e f32 relu microkernel WASM assembly optimized implementation by Frank Barchard · 4 years ago
- bb00b1d AVX512 variants of QS8 GEMM and IGEMM microkernels by Marat Dukhan · 4 years ago