aboutsummaryrefslogtreecommitdiff
AgeCommit message (Expand)Author
2021-02-26QS8 LD64 C4 dot product GEMM microkernel reduced remainder handlingFrank Barchard
2021-02-26QS8 C16 GEMM microkernel source renamed from mull to mlalFrank Barchard
2021-02-26Fix mismatch in block layout in mixed-layout Depth-To-Space operatorMarat Dukhan
2021-02-25QS8 LD32 GEMM microkernel for big cores with dotproductFrank Barchard
2021-02-24C8 MLA Neon GEMM/IGEMM microkernels count k down from kc.Frank Barchard
2021-02-23Enable Quantized C2 microkernel for NeonFrank Barchard
2021-02-23QS8 Neon IGEMM C16 microkernel with two 8 bit multiplies and vpadal to accumu...Frank Barchard
2021-02-22Fix bug in NHWC Convolution with depthwise kernelsMarat Dukhan
2021-02-20[automerger skipped] Mark ab/7061308 as merged in stage. am: 6a70ae05ca -s ou...Xin Li
2021-02-20[automerger skipped] Mark ab/7061308 as merged in stage. am: 6a70ae05ca -s oursXin Li
2021-02-20Mark ab/7061308 as merged in stage.Xin Li
2021-02-19QS8 Neon GEMM C16 microkernel with two 8 bit multiplies and vpadal to accumul...Frank Barchard
2021-02-19Add A55 microkernel to QS8 E2E benchmark.Frank Barchard
2021-02-17[LSC] Add LOCAL_LICENSE_KINDS to external/XNNPACK am: c01162945b am: 582bf80c...Bob Badour
2021-02-17[LSC] Add LOCAL_LICENSE_KINDS to external/XNNPACK am: c01162945b am: 582bf80c12Bob Badour
2021-02-17[LSC] Add LOCAL_LICENSE_KINDS to external/XNNPACK am: c01162945bBob Badour
2021-02-16Remove scalar C4 QS8 and QU8 gemm microkernels.Frank Barchard
2021-02-16QS8 C8 Neon remove remainder handling code and rewind the A pointers by kcFrank Barchard
2021-02-16QS8 e2e benchmark for C2 neon microkernelsFrank Barchard
2021-02-15QS8 C2 Neon igemmFrank Barchard
2021-02-15QS8 C8 Neon igemmFrank Barchard
2021-02-13QS8 scalar gemm remove bias variables.Frank Barchard
2021-02-13Add space after castingFrank Barchard
2021-02-12[LSC] Add LOCAL_LICENSE_KINDS to external/XNNPACKandroid-s-preview-1Bob Badour
2021-02-12Wrap MR=1 end to end benchmarks with #if XNN_ENABLE_E2E_MR1Frank Barchard
2021-02-12Remove 0 from ranges where not neededFrank Barchard
2021-02-11Process 32 pixels at a time in ARM64 SpMM microkernelsMarat Dukhan
2021-02-10Unroll KC loop to do MULL and then MLAL to 16 bit before lengthening to 32 bit.Frank Barchard
2021-02-10E2E run benchmarks from fastest to slowest instruction setFrank Barchard
2021-02-10QS8 e2e benchmark add all x86 microkernels.Frank Barchard
2021-02-09QS8 e2e benchmark add all Web Assembly microkernels.Frank Barchard
2021-02-08QS8 e2e benchmark add all ARM microkernels.Frank Barchard
2021-02-08Reorder a few gemm1 initializations to match end to end order of gemm, igemm,...Jared Duke
2021-02-08qs8-gemm-e2e benchmark for comparing performance of quantized microkernelsFrank Barchard
2021-02-08Reorder a few gemm1 initializations to match end to end order of gemm, igemm,...Frank Barchard
2021-02-05QS8 GEMM for neon reorder with MR inner loop so mull and mlal to avoid depend...Frank Barchard
2021-02-04Merge "Update Android.bp following XNNPACK rebase" am: 1ba03ca626 am: 6560219...Treehugger Robot
2021-02-04Upgrade XNNPACK to db2475b8af7e129b722167c3579ea743735fd733 am: 48d70eb6a7 am...Haibo Huang
2021-02-03C2 QS8 microkernel using mull then mlal with KC loop of 16Frank Barchard
2021-02-04Merge "Update Android.bp following XNNPACK rebase" am: 1ba03ca626 am: 6560219732Treehugger Robot
2021-02-04Upgrade XNNPACK to db2475b8af7e129b722167c3579ea743735fd733 am: 48d70eb6a7 am...Haibo Huang
2021-02-04Merge "Update Android.bp following XNNPACK rebase" am: 1ba03ca626Treehugger Robot
2021-02-04Upgrade XNNPACK to db2475b8af7e129b722167c3579ea743735fd733 am: 48d70eb6a7Haibo Huang
2021-02-04Merge "Update Android.bp following XNNPACK rebase"Treehugger Robot
2021-02-03Update Android.bp following XNNPACK rebaseMiao Wang
2021-01-29QS8 Neon GEMM C8 microkernel with 8 bit multiply and vpadal to accumulate.Frank Barchard
2021-01-27Add MR=1 versions of QS8 gemm benchmarksFrank Barchard
2021-01-27Merge pull request #1273 from powderluv:fix-compileXNNPACK Team
2021-01-26Change isfinite() to std::isfinite()Anush Elangovan
2021-01-22Implement bilinear upsampling (CHW layout) for ARM architectureArtsiom Ablavatski
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-24 17:09:30 +0000