- 83d49b3 Fix builds of QS8 GEMM E2E benchmarks with XNN_ENABLE_FULL_BENCHMARKS=1 by Marat Dukhan · 3 years, 6 months ago
- 3c5892e Benchmark various requantization schemas in QS8 GEMM E2E by Marat Dukhan · 3 years, 6 months ago
- 8102593 Update GEMM benchmarks by Marat Dukhan · 3 years, 6 months ago
- 776fdab Unify U8 MINMAX parameters across NEON and scalar by Marat Dukhan · 3 years, 6 months ago
- 71855ee Support FP32 requantization in AVX512 QS8 microkernels by Marat Dukhan · 3 years, 6 months ago
- d4c7d82 AVX512-specific parameters for QS8 microkernels by Marat Dukhan · 3 years, 6 months ago
- 77ded05 Use byte-wide MIN/MAX in AVX512 QS8 DWCONV microkernels by Marat Dukhan · 3 years, 6 months ago
- 9b474cf Support FP32 requantization in AVX2 QS8 microkernels by Marat Dukhan · 3 years, 6 months ago
- 0a5d7b4 Fix CMake build by Marat Dukhan · 3 years, 6 months ago
- a5d1261 Explicitly specify requantization in GEMM/IGEMM/DWCONV tests by Marat Dukhan · 3 years, 6 months ago
- 5ca0d8d Consolidate requantization structures and functions in a single header by Marat Dukhan · 3 years, 6 months ago
- f86ee8b Refactor requantization helper functions by Marat Dukhan · 3 years, 6 months ago
- 9976cd8 Rename Q31 requantization to GEMMLOWP requantization by Marat Dukhan · 3 years, 6 months ago
- e3d17bf Rename microkernel-related types and structures by Marat Dukhan · 3 years, 6 months ago
- b07c26a Rename QS8 GEMM/IGEMM/DWCONV microkernels by Marat Dukhan · 3 years, 6 months ago
- e1ff248 Rename QS8 DWCONV microkernel filenames by Marat Dukhan · 3 years, 6 months ago
- d65d20e Rename QS8 GEMM/IGEMM microkernel filenames by Marat Dukhan · 3 years, 6 months ago
- c58453f Initialize VMULCADDC microkernel parameters through function pointers by Marat Dukhan · 3 years, 6 months ago
- a0acc15 Use pointer to parameter initialization function in VMULCADDC microkernel tests by Marat Dukhan · 3 years, 6 months ago
- 0b57154 4x16C4 QS8 IGEMM Cortex A75 microkernel reuse X8 to save push by Frank Barchard · 3 years, 6 months ago
- 56fdb25 Increase timeout for QS8 GEMM/IGEMM microkernel tests by Marat Dukhan · 3 years, 6 months ago
- 104ae5e Use ISA-specific layouts in F32 [I]GEMM & DWCONV microkernels by Marat Dukhan · 3 years, 6 months ago
- e091adb 4x16 QS8 GEMM/IGEMM Cortex A53 microkernels reduce to use 2 GPR for temp by Frank Barchard · 3 years, 6 months ago
- 748fd12 Use specialized layouts in SSE4/AVX2 QS8 [I]GEMM & DWCONV microkernels by Marat Dukhan · 3 years, 6 months ago
- 725f47e Split QS8/QU8 GEMM parameter initialization by datatype by Marat Dukhan · 3 years, 6 months ago
- c5a7a39 Initialize GEMM/IGEMM/DWCONV microkernel parameters through function pointers by Marat Dukhan · 3 years, 6 months ago
- 4bb82cc 4x16 QS8 IGEMM microkernels use x8 for temp by Frank Barchard · 3 years, 6 months ago
- 4be4bd7 4x16 QS8 IGEMM microkernels use x14 for A1 by Frank Barchard · 3 years, 6 months ago
- fb672aa 4x16 QS8 IGEMM microkernel for Cortex A53 avoid a push by Frank Barchard · 3 years, 6 months ago
- d5694df Use pointer to parameter initialization function in GEMM/IGEMM/DWCONV microkernel tests by Marat Dukhan · 3 years, 6 months ago
- a8d134b Regenerate F16 GEMM microkernels by Marat Dukhan · 3 years, 6 months ago
- f9fdaa7 Disable applying XNNPACK delegate by default when benchmarking tflite inside XNNPACK/bench because the intention of those benchmarks is to compare the XNNPACK execution path against the original tflite CPU one. by Chao Mei · 3 years, 6 months ago
- d4416d6 4x16 QS8 microkernel for Cortex A53 by Frank Barchard · 3 years, 6 months ago
- f56f4c4 Refactor interface of microkernel parameter initialization by Marat Dukhan · 3 years, 6 months ago
- 5223fd1 Merge pull request #1462 from georgthegreat:patch-1 by XNNPACK Team · 3 years, 6 months ago
- 32ff5ba Update init.c by Yuriy Chernyshov · 3 years, 6 months ago
- 814c249 Workaround -Wincompatible-pointer-types by Yuriy Chernyshov · 3 years, 6 months ago
- a6c0516 Migrate remaining CLAMP and HSWISH tests to VUNARY test gen by Marat Dukhan · 3 years, 6 months ago
- 6eaab71 Remove pointer casting in generated vector unary tests by Marat Dukhan · 3 years, 6 months ago
- 10f1fe0 Rename VBinOpMicrokernelTester -> VBinaryMicrokernelTester by Marat Dukhan · 3 years, 6 months ago
- 87ed45c Rename VUnOpMicrokernelTester -> VUnaryMicrokernelTester by Marat Dukhan · 3 years, 6 months ago
- 60d3f24 Migrate F32 VCLAMP microkernel tests to VUNARY test gen by Marat Dukhan · 3 years, 6 months ago
- 949b6e7 Migrate F32 HSWISH microkernel tests to VUNARY test gen by Marat Dukhan · 3 years, 6 months ago
- 4ed1488 QS8 DWCONV25 microkernels by Marat Dukhan · 3 years, 6 months ago
- 76f43f0 Apply consistent formatting to assembly by Frank Barchard · 3 years, 6 months ago
- 15a35c0 Optimize QS8 GEMM/IGEMM selection on RISC-V by Marat Dukhan · 3 years, 6 months ago
- a24cc08 Small refactoring of scalar QS8 microkernels by Marat Dukhan · 3 years, 6 months ago
- 803c1f8 Enable QS8 microkernels on WAsm and RISC-V by Marat Dukhan · 3 years, 6 months ago
- d481c28 QS8 VADD microkernels by Marat Dukhan · 3 years, 6 months ago
- 047b620 Scalar QS8 GAVGPOOL microkernels by Marat Dukhan · 3 years, 6 months ago
- 4454288 Scalar QS8 DWCONV microkernels by Marat Dukhan · 3 years, 6 months ago
- b77be26 Enable 1x8C8 a75 nicrokernel for Cortex A75 by Frank Barchard · 3 years, 6 months ago
- a1a4e78 Scalar QS8 GEMM and IGEMM microkernels by Marat Dukhan · 3 years, 6 months ago
- 938ea81 Code generate 1x8C8 nicrokernel for Cortex A75 with and without prfm by Frank Barchard · 3 years, 6 months ago
- cbfa338 text format white space of prefetch instruction on ARM microkernels by Frank Barchard · 3 years, 6 months ago
- e3cb19b Minimal RISC-V support by Marat Dukhan · 3 years, 6 months ago
- b9ebcad Fix CMake build by Marat Dukhan · 3 years, 6 months ago
- b639210 Add prefetch of A for quantized microkernels. by Frank Barchard · 3 years, 6 months ago
- a91559a Move declarations of VHSWISH microkernels into vunary.h by Marat Dukhan · 3 years, 6 months ago
- b1eec08 Refactor filenames of Clamp/Relu/Sigmoid microkernels by Marat Dukhan · 3 years, 6 months ago
- 43558a7 Fix CMake build for ARM64 by Marat Dukhan · 3 years, 6 months ago
- 6674d69 Refactor naming of unary elementwise microkernels by Marat Dukhan · 3 years, 6 months ago
- 3a6bb68 Merge pull request #1426 from microblink:mb-patches by XNNPACK Team · 3 years, 6 months ago
- e111861 1x8 C8 A53 microkernel defer adap by Frank Barchard · 3 years, 6 months ago
- 7c4c771 C8 A53 microkernels prefetch A by Frank Barchard · 3 years, 6 months ago
- 2a3169d C8 A53 microkernels move 2nd load after MLA by Frank Barchard · 3 years, 6 months ago
- ec51a4e Enable QS8 1x8C8 IGEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 7 months ago
- dddb38f QS8 1x8C8 IGEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 7 months ago
- 21acdd0 Enable QS8 1x8C8 GEMM microkernel for Cortex A53. by Frank Barchard · 3 years, 7 months ago
- 46a69c9 QS8 1x8C8 GEMM microkernel for Cortex A53 by Frank Barchard · 3 years, 7 months ago
- 042cdaf GCC 11 no longer needs this polyfill by Nenad Mikša · 3 years, 7 months ago
- 93757bf add `*.swp` to .gitignore by Nenad Mikša · 3 years, 7 months ago
- 2de3bce A53 C8 microkernel load A with ldr/ldr/ins by Frank Barchard · 3 years, 7 months ago
- 184a8e1 Enable A53 C8 microkernel load A with ldr/ldr/ins by Frank Barchard · 3 years, 7 months ago
- 5549735 4X8 and 4x16 mla lane microkernels for A53 by Frank Barchard · 3 years, 7 months ago
- 90f520b Enable Cortex A53 tuned C8 gemm/igemm microkernels for Cortex A53 and Cortex A55r0 by Frank Barchard · 3 years, 7 months ago
- d68e114 Cortex A53 tuned C8 gemm/igemm microkernels by Frank Barchard · 3 years, 7 months ago
- fb5983d Enable prefetch to MLA lane microkernel on Cortex A53 by Frank Barchard · 3 years, 7 months ago
- 1f51d38 Add prefetch to MLA lane microkernel by Frank Barchard · 3 years, 7 months ago
- 8f15372 Expose QS8 Fully Connected operator in Subgraph API by Marat Dukhan · 3 years, 7 months ago
- a999225 Support 2D Convolution and 2D Depthwise Convolution without bias by Marat Dukhan · 3 years, 7 months ago
- 853bb7a Reformat Subgraph API documentation by Marat Dukhan · 3 years, 7 months ago
- d74a53f Improve docs for xnn_define_fully_connected by Marat Dukhan · 3 years, 7 months ago
- 281f13e Simplify Fully Connected Node without bias by Marat Dukhan · 3 years, 7 months ago
- 4c6640c Disable MSan in QS8 GEMM/IGEMM microkernels with KR>1 by Marat Dukhan · 3 years, 7 months ago
- d9487b8 Merge pull request #1409 from larryliu0820:patch-1 by XNNPACK Team · 3 years, 7 months ago
- 3dd80b3 Fix allocator initialize issue on Windows by Larry Liu · 3 years, 7 months ago
- 676322f Merge pull request #1396 from huningxin:fully_connected by XNNPACK Team · 3 years, 7 months ago
- 6ac1d18 Cortex A53 used MLAL lane by Frank Barchard · 3 years, 7 months ago
- c77fc4c Bug fix add missing break for qs8 select on big core. by Frank Barchard · 3 years, 7 months ago
- 2b26670 Merge pull request #1406 from larryliu0820:master by XNNPACK Team · 3 years, 7 months ago
- 39c539d Fix neon v8 for ios armv7 by Larry Liu · 3 years, 7 months ago
- ec56b7e Avoid selection of NEON-DOT microkernels on AArch32 iOS by Marat Dukhan · 3 years, 7 months ago
- 2a995e7 Enable PRFM variant of QS8 C8 Neon microkernel on Cortex A53, A72, A73 and Kryo. by Frank Barchard · 3 years, 7 months ago
- 4a35204 PRFM variant of QS8 C8 Neon microkernel. by Frank Barchard · 3 years, 7 months ago
- 6e8c0ce Disable compilation of neondot microkernels for AArch32 iOS by Marat Dukhan · 3 years, 7 months ago
- 3fd4e27 XOP versions of QS8 DWCONV MUL32 microkernels by Marat Dukhan · 3 years, 7 months ago
- 4181f94 Optimize QS8 GEMM/IGEMM microkernel selection for AVX by Marat Dukhan · 3 years, 7 months ago
- 2e42787 2x4c2/3x4c2 microkernels for SSE2/SSSE3/SSE4.1/AVX/XOP by Marat Dukhan · 3 years, 7 months ago
- 30fa853 Support flags and optional bias for fully_connected node by Ningxin Hu · 3 years, 7 months ago