fbarchard

There are a couple more issues with amx detect, but I'm not sure they are in the scope of pytorch/cpuinfo detect os support for amx on windows, linux etc. detect/enable...

SPMM was only implemented on ARM and WASMSIMD. Unless there is a real usecase for it, I'd suggest making RISC-V follow what Intel did for this, disabling/skipping SPMM. SPMM gives...

The term FFI seems to mean you want to call cpuinfo from other languages, such as Cobol :-) I have no strong opinion on the content of this PR, aside...

needs an update for build changes... there should not be an amalgam/gen folder.

Thanks for the report Looking at the original version, it used to be floats but was recently changed to int. I found the change that did it, but its not...

I found int and int32_t variations of this, and fixed those. Now its just the float extern that is sometimes used. grep extern.*xnn_table_exp2minus_k_over_ . -r -h | sort | uniq...

You can use models/benchmark with --num-threads=2 etc bazel build -c opt :bench/models:benchmark models/benchmark --benchmark_filter=V2 ------------------------------------------------------------------------------------ Benchmark Time CPU Iterations UserCounters... ------------------------------------------------------------------------------------ FP32MobileNetV2/real_time 5327 us 5326 us 127 cpufreq=3.32637G FP16MobileNetV2/real_time 16901...

This is just a wrapper? xnn_pf32_gemm_minmax_ukernel_32x32__neonsme that calls xnn_pf32_gemm_minmax__asm_aarch64_neonsme? // Wraps the `xnn_pf32_gemm_minmax__asm_aarch64_neonsme` // GEMM microkernel with a name that is compatible with our tooling. void xnn_pf32_gemm_minmax_ukernel_32x32__neonsme( size_t m, size_t...

There is another PR that eliminates XNN_PLATFORM_MOBILE, which would also satisfy this Android requirement? https://github.com/google/XNNPACK/pull/8509 This PR would fully enable all x86 microkernels on all devices. If the NDK doesnt...

There are build warnings on the scalar kernel? third_party/XNNPACK/src/qb4-packw/gen/qb4-packw-x16c4-gemm-goi-scalar.c:23:38: error: cast from 'const unsigned char *' to 'unsigned int *' drops const qualifier [-Werror,-Wcast-qual] 23 | const uint32_t s_v0 =...