- 88d06fc Disable neondot microkernels on iOS 32 bit by Frank Barchard · 2 years, 8 months ago
- cde8bdf Q8 GEMM for Cortex A7 reduce prefetch to weights by Frank Barchard · 2 years, 8 months ago
- 3e3124e Make void* params argument of JIT generators const by Zhi An Ng · 2 years, 8 months ago
- 34251d8 QS8 4x8 lane GEMM AArch32 microkernel for Cortex A7 by Frank Barchard · 2 years, 8 months ago
- 9e4d2aa QS8 4x8 lane GEMM AArch32 microkernel for Cortex A53 by Frank Barchard · 2 years, 8 months ago
- 3ceb4f1 Reoptimize NEON QC8/QS8 GEMM/IGEMM microkernels with SR > 1 by Marat Dukhan · 2 years, 8 months ago
- 69b7f14 Reoptimize QS8/QC8 GEMM/IGEMM WAsm SIMD microkernels with swizzle by Marat Dukhan · 2 years, 8 months ago
- fbd67a7 Pad K to a multiple of SR in GEMM/IGEMM microkernels by Marat Dukhan · 2 years, 8 months ago
- c607028 Remove wb from JIT aarch32 instructions, use mem operand and ++ instead by Zhi An Ng · 2 years, 8 months ago
- 870108c QS8/QC8 4x8 dot product IGEMM AArch32 microkernel for Cortex A55 by Frank Barchard · 2 years, 8 months ago
- adf087d Remove 3 blank lines after last jit assembly instruction before end of function by Frank Barchard · 2 years, 8 months ago
- 752b980 Avoid importing the entire xnnpack namespace in aarch32 assembler by Zhi An Ng · 2 years, 8 months ago
- e1ff738 Update assembly register usage comments. by Frank Barchard · 2 years, 8 months ago
- ac654f1 QC8 4x8 dot product GEMM AArch32 microkernel for Cortex A55 by Frank Barchard · 2 years, 8 months ago
- 1e277fd Bug fixes for QS8 Cortex A55 by Frank Barchard · 2 years, 8 months ago
- 0f294ad QS8 4x8 dot product GEMM AArch32 microkernel for Cortex A55 by Frank Barchard · 2 years, 8 months ago
- 901845c QU8 4x8 NEON MLA Lane microkernel AArch32 assembly language by Frank Barchard · 2 years, 8 months ago
- 5e1a303 QC8 GEMM/IGEMM assembly microkernels for ARMv7 NEON by Frank Barchard · 2 years, 8 months ago
- 83844ae Change JIT generator signature to accept nc and kc to specialize on those values by Zhi An Ng · 2 years, 8 months ago
- 48d74c3 Replicate QC8/QS8/QU8 CONV WAsm SIMD parameters to 64 bit rather than 128 bit by Marat Dukhan · 2 years, 9 months ago
- 13b57dd Add more converted microkernels used in init.c. by Zhi An Ng · 2 years, 9 months ago
- 7c1115f Reoptimize microkernel selection for WAsm 1.0 by Marat Dukhan · 2 years, 9 months ago
- cccb012 Apply sort and formatting to ARM code by Frank Barchard · 2 years, 9 months ago
- 272d4d9 FP32 IMAGIC variants of scalar QC8/QS8/QU8 GEMM/IGEMM/DWCONV microkernels by Marat Dukhan · 2 years, 9 months ago
- 2ac722e Refactor requantization in scalar QS8/QC8/QU8 microkernels by Marat Dukhan · 2 years, 9 months ago
- dc54e12 Replace vshll_n_u32(v, 0) with vmovl_u32 in C4/C4S2 GEMM/IGEMM microkernels by Marat Dukhan · 2 years, 9 months ago
- 87fe410 QC8 quantization for all aarch32 GEMM/IGEMM microkernels by Frank Barchard · 2 years, 9 months ago
- a2f1891 Add _prfm to names on Neon microkernels in a consistent way. by Frank Barchard · 2 years, 9 months ago
- 1669dd0 aarch32 avoid the VPUSH/VPOP of unused registers by Frank Barchard · 2 years, 9 months ago
- 70e8c99 Format source and BUILD file by Frank Barchard · 2 years, 9 months ago
- 9f3f420 QS8 4x8 LD64 dot product GEMM AArch32 microkernel by Frank Barchard · 2 years, 9 months ago
- 7bd7ecc qs8 4x8 aarch32/64 GEMM/IGEMM improved prefetch scheduling. by Frank Barchard · 2 years, 9 months ago
- d541fc0 Annotate remaining microkernels with Out-of-Bounds reads with XNN_OOB_READS by Marat Dukhan · 2 years, 9 months ago
- da7b2e2 QS8 4x8 lane GEMM AArch32 microkernel by Frank Barchard · 2 years, 9 months ago
- 914f57b Aarch64 4x8 lane ld64 GEMM/IGEMM microkernels. by Frank Barchard · 2 years, 9 months ago
- 0f1ed94 QS8/QC8 GEMM/IGEMM WAsm SIMD microkernels using C2S4 layout by Marat Dukhan · 2 years, 10 months ago
- 03efa0f Reoptimize FP32 requantization in NEON QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 10 months ago
- 5a31dc6 Optimize FP32 requantization in NEON QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 10 months ago
- 7988a18 Refactoring xnn_qs8_minmax_params for NEON/NEONv8 by Marat Dukhan · 2 years, 10 months ago
- 8978ac2 Support requantization scale greater than 1 in RNDNU NEON microkernels by Marat Dukhan · 2 years, 10 months ago
- 13c9f8d Support requantization scale over 1 in SSE/AVX GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 10 months ago
- 8999190 Remove GEMMLOWP requantization from QS8 GEMM/IGEMM templates by Marat Dukhan · 2 years, 10 months ago
- 411c18d Optimize FP32 requantization in WAsm SIMD QS8/QC8/QU8 GEMM/IGEMM/DWCONV by Marat Dukhan · 2 years, 10 months ago
- 19c8644 Fix prefetch offset for QS8 lane prfm GEMM/IGEMM microkernels/ by Frank Barchard · 2 years, 10 months ago
- 5f7cf55 Avoid using gcc-specific intrinsics in NEON microkernels by Marat Dukhan · 2 years, 10 months ago
- 27bf92c RNDNU versions of all Neon lane microkernels. by Frank Barchard · 2 years, 10 months ago
- 5cffb64 4x16 lane AArch64 NEON GEMM/IGEMM ld64 microkernel by Frank Barchard · 2 years, 10 months ago
- 64ab1b7 LD1R and LD2R variants of c4 microkernel by Frank Barchard · 2 years, 10 months ago
- 15eec02 LD1R and LD2R variants of c2 microkernel by Frank Barchard · 2 years, 10 months ago
- 42f5c50 LOADDUP variant of c2 microkernel by Frank Barchard · 2 years, 10 months ago
- e22685a Remove padal from quantized microkernel names. by Frank Barchard · 2 years, 11 months ago
- eb704f7 QS8 C4S2 Neon GEMM/IGEMM microkernels by Frank Barchard · 2 years, 11 months ago
- c7a032d C2S4 QS8 Neon GEMM/IGEMM microkernels. by Frank Barchard · 2 years, 11 months ago
- 287952a QS8 C4 Neon GEMM/IGEMM microkernels by Frank Barchard · 2 years, 11 months ago
- 494cd2b S4 variant of C2 Neon GEMM/IGEMM microkernel by Frank Barchard · 2 years, 11 months ago
- 952cb51 S4 variant of C2 Neon GEMM/IGEMM mull microkernel by Frank Barchard · 2 years, 11 months ago
- ccbaedf C2 Neon microkernel remove duplicate DUP instructions from NR loop. by Frank Barchard · 2 years, 11 months ago
- 1d41247 Neon C2 microkernels switch to rndnu from gemmlowp by Frank Barchard · 2 years, 11 months ago
- 0bf8afa Leverage f32x4.pmin and f32x4.pmax WAsm SIMD instructions by Marat Dukhan · 3 years ago
- 031ff4b Template bug fix in stores for remainder of 8 in Neon QS8 microkernels by Frank Barchard · 3 years, 1 month ago
- ec5c129 Template bug fix in stores for remainder of 8. by Frank Barchard · 3 years, 1 month ago
- 4c49494 Fix crash on AArch32 in scalar quantized microkernels by Marat Dukhan · 3 years, 1 month ago
- 1ce78ab Leverage Load-Zero WAsm SIMD instructions in Chrome M88 microkernels by Marat Dukhan · 3 years, 1 month ago
- b7a7c30 NEON GEMM/IGEMM microkernels change store/dup to 2 of each by Frank Barchard · 3 years, 1 month ago
- 132774e QU8 microkernels change stores to non-lane STR by Frank Barchard · 3 years, 1 month ago
- 29833fd Change stores to non-lane STR by Frank Barchard · 3 years, 1 month ago
- 1c70764 4x16c4 cortex_a55 microkernel tuning by Frank Barchard · 3 years, 1 month ago
- a49e41f QU8 4x16C4 NEON Dot Product GEMM/IGEMM microkernels for Cortex A55r1 by Frank Barchard · 3 years, 1 month ago
- 4810905 Leverage v128.const WAsm SIMD instruction by Marat Dukhan · 3 years, 1 month ago
- 8dc106e QC8/QS8/QU8 GEMM/IGEMM WAsm SIMD microkernels using i32x4.dot_i16x8_s instruction by Marat Dukhan · 3 years, 1 month ago
- 1215c9a QS8 NEON GEMM microkernels use rewind instead of reload by Frank Barchard · 3 years, 1 month ago
- 6b30b73 Remainder branch move before label. by Frank Barchard · 3 years, 1 month ago
- 56f157c Relabel branches for quantized assembly ARM microkernels by Frank Barchard · 3 years, 1 month ago
- 7a8dd87 Work around generating v128.storeXX_lane for quantized WAsm SIMD microkernels by Marat Dukhan · 3 years, 1 month ago
- 0c2a31e Improve unpacking in SSE4+ QC8/QS8/QU8 GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 1 month ago
- b43c5ef Fix indent on C4 Neon Dot Product GEMM/IGEMM microkernels by Frank Barchard · 3 years, 2 months ago
- 07706f6 Replace generic shuffle with narrow instructions in WAsm SIMD QS8/QU8/QC8 microkernels by Marat Dukhan · 3 years, 2 months ago
- dfc2db0 Add prefix to QC8/QS8/QU8 WAsm SIMD GEMM/IGEMM microkernels by Marat Dukhan · 3 years, 2 months ago
- 3e9dc22 Remove WAsm SIMD GEMM/IGEMM microkernels with GEMMLOWP requantization by Marat Dukhan · 3 years, 2 months ago
- 4486f87 Prune NEON-DOT QS8 GEMM/IGEMM microkernels with FP32 & GEMMLOWP requantization by Marat Dukhan · 3 years, 2 months ago
- 400e7cb Prune WAsm SIMD QS8 GEMM/IGEMM microkernels with GEMMLOWP requantization by Marat Dukhan · 3 years, 2 months ago
- e16bf7d Prune AVX2/AVX512 QS8 GEMM/IGEMM microkernels with GEMMLOWP requantization by Marat Dukhan · 3 years, 2 months ago
- 8674629 Use QS8 GEMM WAsm SIMD microkernels with FP32 requantization in the benchmark by Marat Dukhan · 3 years, 2 months ago
- 0ff7989 Use FP32 requantization for extended-weights QS8 GEMM microkernels on x86 by Marat Dukhan · 3 years, 2 months ago
- ec47958 Prune redundant NEON GEMM/IGEMM microkernels with GEMMLOWP requantization by Marat Dukhan · 3 years, 2 months ago
- d4db6af Replace wasm_i32x4_lt(vzero, vXX) with wasm_i32x4_shr(vXX, 31) by Marat Dukhan · 3 years, 2 months ago
- 2c6d196 Q8 4x16 and 1x16 Neon GEMM/IGEMM quantize using V0-V3 by Frank Barchard · 3 years, 2 months ago
- fb3a94f QU8 4x16 Neon assembly microkernel for Cortex A75 by Frank Barchard · 3 years, 2 months ago
- 86a1618 QU8 Neon params replace pad with duplicated zero_point by Frank Barchard · 3 years, 2 months ago
- 59ed1da QU8 4x16 Neon assembly microkernel by Frank Barchard · 3 years, 2 months ago
- 6967eb0 Add a rewind variable for params. - no impact on code, just simplified source by Frank Barchard · 3 years, 2 months ago
- 510b8e0 Code generator for RNDNU quantization mode on neon-mull-addw-dup microkernel by Frank Barchard · 3 years, 2 months ago
- 26e8378 Reduce register pressure in GEMMLOWP quantization on NEON by Frank Barchard · 3 years, 2 months ago
- 1a2dbe1 RNDNU scalar GEMM/IGEMM microkernel by Frank Barchard · 3 years, 2 months ago
- efa123d Update Neon code with generators for added comment by Frank Barchard · 3 years, 2 months ago
- 22fbe77 RNDNU quantized 1x16 and 4x16 Neon lane GEMM/IGEMM microkernels. by Frank Barchard · 3 years, 2 months ago
- 13db60f RNDNU quantized Neon assembly GEMM/IGEMM microkernels. by Frank Barchard · 3 years, 2 months ago
- 60729d0 4x16c4 RNDNU quantized Neon assembly GEMM/IGEMM microkernel. by Frank Barchard · 3 years, 2 months ago
- e903dff QS8 GEMM/IGEMM microkernels with RNDNU requantization by Marat Dukhan · 3 years, 2 months ago
- 2837e8b Remove 0 offset from loads. by Frank Barchard · 3 years, 2 months ago