fbarchard

looking at this function in particular, its not actually using fp16 arithmetics xnn_f16_vabs_ukernel__neonfp16arith_u16 the type is f16, but the implementation is actually neon. the file name is neon, and inconsistent...

Could you fill in all the microarchitectures? When I run sde, the following show unknown: ./gnr256/cpuinfo.txt- 36x unknown ./rpl/cpuinfo.txt- 36x unknown ./lnl/cpuinfo.txt- 36x unknown ./snr/cpuinfo.txt- 36x unknown ./adl/cpuinfo.txt- 36x unknown...

You could start with just the P-Core uarch and add hybrid in a followup PR. Note that Alderlake has 2 'models', depending if you've got e-cores enabled or not.

looks good overall. you call this m4 but store is m1? in gemm config you set NR to 4 * hardware_config->vlenb / sizeof(int32_t); The elements are 8 bit and you...

I think this is a case of invalid parameters for 5x5. In practice 5x5 is used by mobilenet v3, while 3x3 is used in mobilenet v2. So you could try...

Hi, thanks for the report. I think you just want avx512 disabled, not avx2 etc? Is that error showing something more specific, like a header or intrinsic that fails? If...

xnnpack supports SSE and x86 32 bit. In practice its getting hard to test on anything less than SSE4.2 The lowest end cpu I've tested on recently is Intel Silvermont,...

bazel on linux is currently broken, and likely would occur on all x86 platforms XNNPACK/BUILD.bazel:640:8: declared output 'testdata/cmake/gen/avx512bf16_microkernels.cmake' was not created by genrule. normally the flag `--define xnn_enable_avx512bf16=false` would work...

FWIW we now have tests running using Intel SDE that ensure XNNPack runs on Intel Silvermont (Atom) which has SSE4.1 but not AVX. The tests pass on both Windows and...

Note that the following code, to check for linux kernel support, does not work in chromium sandbox? ```cpp #if (defined(__i386__) || defined(__x86_64__)) && defined(__linux__) #define ARCH_REQ_XCOMP_PERM 0x1023 #define XFEATURE_XTILEDATA 18...