Directory listing for /PyTorch/test/pytorch/third_party/XNNPACK/src/f32-gemm/gen/
f32-gemm-10x16-minmax-avx512f-broadcast.c
f32-gemm-10x32-minmax-avx512f-broadcast.c
f32-gemm-10x64-minmax-avx512f-broadcast.c
f32-gemm-11x16-minmax-avx512f-broadcast.c
f32-gemm-11x32-minmax-avx512f-broadcast.c
f32-gemm-11x64-minmax-avx512f-broadcast.c
f32-gemm-12x16-minmax-avx512f-broadcast.c
f32-gemm-12x32-minmax-avx512f-broadcast.c
f32-gemm-12x64-minmax-avx512f-broadcast.c
f32-gemm-13x16-minmax-avx512f-broadcast.c
f32-gemm-13x32-minmax-avx512f-broadcast.c
f32-gemm-13x64-minmax-avx512f-broadcast.c
f32-gemm-14x16-minmax-avx512f-broadcast.c
f32-gemm-14x32-minmax-avx512f-broadcast.c
f32-gemm-14x64-minmax-avx512f-broadcast.c
f32-gemm-15x16-minmax-avx512f-broadcast.c
f32-gemm-15x32-minmax-avx512f-broadcast.c
f32-gemm-15x64-minmax-avx512f-broadcast.c
f32-gemm-16x16-minmax-avx512f-broadcast.c
f32-gemm-16x32-minmax-avx512f-broadcast.c
f32-gemm-16x32-minmax-hvx-broadcast.c
f32-gemm-16x64-minmax-avx512f-broadcast.c
f32-gemm-1x12-minmax-asm-aarch64-neonfma-cortex-a53.S
f32-gemm-1x128-minmax-hvx-broadcast.c
f32-gemm-1x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-1x16-minmax-avx-broadcast.c
f32-gemm-1x16-minmax-avx512f-broadcast.c
f32-gemm-1x16-minmax-fma3-broadcast.c
f32-gemm-1x16-minmax-neon-lane-ld128.c
f32-gemm-1x16s4-minmax-fma3-broadcast.c
f32-gemm-1x32-minmax-avx512f-broadcast.c
f32-gemm-1x32-minmax-hvx-broadcast.c
f32-gemm-1x4-minmax-scalar.c
f32-gemm-1x4-minmax-wasm.c
f32-gemm-1x4-relu-scalar.c
f32-gemm-1x4-relu-wasm.c
f32-gemm-1x4-scalar.c
f32-gemm-1x4v-minmax-rvv.c
f32-gemm-1x4v-relu-rvv.c
f32-gemm-1x4v-rvv.c
f32-gemm-1x64-minmax-avx512f-broadcast.c
f32-gemm-1x64-minmax-hvx-broadcast.c
f32-gemm-1x8-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-1x8-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-1x8-minmax-asm-aarch32-neon-cortex-a53-prfm.S
f32-gemm-1x8-minmax-asm-aarch32-neon-cortex-a53.S
f32-gemm-1x8-minmax-asm-aarch64-neon-ld128-acc2-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neon-ld128-acc2.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-cortex-a53-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-cortex-a53.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-cortex-a75-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-cortex-a75.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128-acc2-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128-acc2.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128-acc4-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128-acc4.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64-acc2-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64-acc2.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64-acc4-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64-acc4.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64-prfm.S
f32-gemm-1x8-minmax-asm-aarch64-neonfma-ld64.S
f32-gemm-1x8-minmax-avx-broadcast.c
f32-gemm-1x8-minmax-fma3-broadcast.c
f32-gemm-1x8-minmax-neon-dup-ld64.c
f32-gemm-1x8-minmax-neon-lane-ld128.c
f32-gemm-1x8-minmax-neon-lane-ld64.c
f32-gemm-1x8-minmax-neonfma-dup-ld64.c
f32-gemm-1x8-minmax-sse-dup.c
f32-gemm-1x8-minmax-sse-load1.c
f32-gemm-1x8-minmax-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-1x8-minmax-wasmrelaxedsimd-fma-splat.c
f32-gemm-1x8-minmax-wasmrelaxedsimd-loadsplat.c
f32-gemm-1x8-minmax-wasmrelaxedsimd-splat.c
f32-gemm-1x8-minmax-wasmsimd-arm-loadsplat.c
f32-gemm-1x8-minmax-wasmsimd-arm-splat.c
f32-gemm-1x8-minmax-wasmsimd-x86-loadsplat.c
f32-gemm-1x8-minmax-wasmsimd-x86-splat.c
f32-gemm-1x8-relu-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-1x8-relu-wasmrelaxedsimd-fma-splat.c
f32-gemm-1x8-relu-wasmsimd-loadsplat.c
f32-gemm-1x8-relu-wasmsimd-splat.c
f32-gemm-1x8-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-1x8-wasmrelaxedsimd-fma-splat.c
f32-gemm-1x8-wasmsimd-loadsplat.c
f32-gemm-1x8-wasmsimd-splat.c
f32-gemm-1x8s4-minmax-neon.c
f32-gemm-1x8s4-minmax-neonfma.c
f32-gemm-1x8s4-minmax-sse.c
f32-gemm-1x8s4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-1x8s4-minmax-wasmrelaxedsimd.c
f32-gemm-1x8s4-minmax-wasmsimd-arm.c
f32-gemm-1x8s4-minmax-wasmsimd-x86.c
f32-gemm-1x8s4-relu-wasmrelaxedsimd-fma.c
f32-gemm-1x8s4-relu-wasmsimd.c
f32-gemm-1x8s4-wasmrelaxedsimd-fma.c
f32-gemm-1x8s4-wasmsimd.c
f32-gemm-2x128-minmax-hvx-broadcast.c
f32-gemm-2x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-2x16-minmax-neon-lane-ld128.c
f32-gemm-2x4-minmax-scalar.c
f32-gemm-2x4-minmax-wasm.c
f32-gemm-2x4-relu-scalar.c
f32-gemm-2x4-relu-wasm.c
f32-gemm-2x4-scalar.c
f32-gemm-3x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-3x16-minmax-avx-broadcast.c
f32-gemm-3x16-minmax-fma3-broadcast.c
f32-gemm-3x16-minmax-neon-lane-ld128.c
f32-gemm-3x16s4-minmax-fma3-broadcast.c
f32-gemm-3x8-minmax-sse-dup.c
f32-gemm-3x8-minmax-sse-load1.c
f32-gemm-3x8-minmax-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-3x8-minmax-wasmrelaxedsimd-fma-splat.c
f32-gemm-3x8-minmax-wasmrelaxedsimd-loadsplat.c
f32-gemm-3x8-minmax-wasmrelaxedsimd-splat.c
f32-gemm-3x8-minmax-wasmsimd-arm-loadsplat.c
f32-gemm-3x8-minmax-wasmsimd-arm-splat.c
f32-gemm-3x8-minmax-wasmsimd-x86-loadsplat.c
f32-gemm-3x8-minmax-wasmsimd-x86-splat.c
f32-gemm-3x8-relu-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-3x8-relu-wasmrelaxedsimd-fma-splat.c
f32-gemm-3x8-relu-wasmsimd-loadsplat.c
f32-gemm-3x8-relu-wasmsimd-splat.c
f32-gemm-3x8-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-3x8-wasmrelaxedsimd-fma-splat.c
f32-gemm-3x8-wasmsimd-loadsplat.c
f32-gemm-3x8-wasmsimd-splat.c
f32-gemm-3x8s4-minmax-sse.c
f32-gemm-3x8s4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-3x8s4-minmax-wasmrelaxedsimd.c
f32-gemm-3x8s4-minmax-wasmsimd-arm.c
f32-gemm-3x8s4-minmax-wasmsimd-x86.c
f32-gemm-3x8s4-relu-wasmrelaxedsimd-fma.c
f32-gemm-3x8s4-relu-wasmsimd.c
f32-gemm-3x8s4-wasmrelaxedsimd-fma.c
f32-gemm-3x8s4-wasmsimd.c
f32-gemm-4x1-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-4x1-minmax-asm-aarch64-neonfma-ld64.S
f32-gemm-4x12-minmax-asm-aarch64-neonfma-cortex-a53.S
f32-gemm-4x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-4x16-minmax-avx-broadcast.c
f32-gemm-4x16-minmax-avx512f-broadcast.c
f32-gemm-4x16-minmax-fma3-broadcast.c
f32-gemm-4x16-minmax-neon-lane-ld128.c
f32-gemm-4x16s4-minmax-fma3-broadcast.c
f32-gemm-4x2-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-4x2-minmax-asm-aarch64-neonfma-cortex-a75-prfm.S
f32-gemm-4x2-minmax-asm-aarch64-neonfma-cortex-a75.S
f32-gemm-4x2-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-4x2-minmax-asm-aarch64-neonfma-ld64.S
f32-gemm-4x2-minmax-neon-lane-ld64.c
f32-gemm-4x2-minmax-scalar.c
f32-gemm-4x2-minmax-wasm.c
f32-gemm-4x2-relu-scalar.c
f32-gemm-4x2-relu-wasm.c
f32-gemm-4x2-scalar.c
f32-gemm-4x2c4-minmax-sse.c
f32-gemm-4x2c4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-4x2c4-minmax-wasmrelaxedsimd.c
f32-gemm-4x2c4-minmax-wasmsimd-arm.c
f32-gemm-4x2c4-minmax-wasmsimd-x86.c
f32-gemm-4x2c4-relu-wasmrelaxedsimd-fma.c
f32-gemm-4x2c4-relu-wasmsimd.c
f32-gemm-4x2c4-wasmrelaxedsimd-fma.c
f32-gemm-4x2c4-wasmsimd.c
f32-gemm-4x32-minmax-avx512f-broadcast.c
f32-gemm-4x4-asm-aarch32-vfp-ld64.S
f32-gemm-4x4-minmax-asm-aarch32-vfp-ld64.S
f32-gemm-4x4-minmax-scalar.c
f32-gemm-4x4-minmax-wasm.c
f32-gemm-4x4-relu-scalar.c
f32-gemm-4x4-relu-wasm.c
f32-gemm-4x4-scalar.c
f32-gemm-4x64-minmax-avx512f-broadcast.c
f32-gemm-4x64-minmax-hvx-broadcast.c
f32-gemm-4x8-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-4x8-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a53-prfm.S
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a53.S
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a55.S
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a7.S
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a75-prfm.S
f32-gemm-4x8-minmax-asm-aarch32-neon-cortex-a75.S
f32-gemm-4x8-minmax-asm-aarch32-neon-ld64.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-cortex-a53-prfm.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-cortex-a53.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-cortex-a55.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-cortex-a75-prfm.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-cortex-a75.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-4x8-minmax-asm-aarch64-neonfma-ld64.S
f32-gemm-4x8-minmax-avx-broadcast.c
f32-gemm-4x8-minmax-fma3-broadcast.c
f32-gemm-4x8-minmax-neon-dup-ld128.c
f32-gemm-4x8-minmax-neon-dup-ld64.c
f32-gemm-4x8-minmax-neon-lane-ld128.c
f32-gemm-4x8-minmax-neon-lane-ld64.c
f32-gemm-4x8-minmax-neonfma-dup-ld128.c
f32-gemm-4x8-minmax-neonfma-dup-ld64.c
f32-gemm-4x8-minmax-sse-dup.c
f32-gemm-4x8-minmax-sse-load1.c
f32-gemm-4x8-minmax-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-4x8-minmax-wasmrelaxedsimd-fma-splat.c
f32-gemm-4x8-minmax-wasmrelaxedsimd-loadsplat.c
f32-gemm-4x8-minmax-wasmrelaxedsimd-splat.c
f32-gemm-4x8-minmax-wasmsimd-arm-loadsplat.c
f32-gemm-4x8-minmax-wasmsimd-arm-splat.c
f32-gemm-4x8-minmax-wasmsimd-x86-loadsplat.c
f32-gemm-4x8-minmax-wasmsimd-x86-splat.c
f32-gemm-4x8-relu-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-4x8-relu-wasmrelaxedsimd-fma-splat.c
f32-gemm-4x8-relu-wasmsimd-loadsplat.c
f32-gemm-4x8-relu-wasmsimd-splat.c
f32-gemm-4x8-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-4x8-wasmrelaxedsimd-fma-splat.c
f32-gemm-4x8-wasmsimd-loadsplat.c
f32-gemm-4x8-wasmsimd-splat.c
f32-gemm-4x8s4-minmax-neon.c
f32-gemm-4x8s4-minmax-neonfma.c
f32-gemm-4x8s4-minmax-sse.c
f32-gemm-4x8s4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-4x8s4-minmax-wasmrelaxedsimd.c
f32-gemm-4x8s4-minmax-wasmsimd-arm.c
f32-gemm-4x8s4-minmax-wasmsimd-x86.c
f32-gemm-4x8s4-relu-wasmrelaxedsimd-fma.c
f32-gemm-4x8s4-relu-wasmsimd.c
f32-gemm-4x8s4-wasmrelaxedsimd-fma.c
f32-gemm-4x8s4-wasmsimd.c
f32-gemm-5x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-5x16-minmax-avx-broadcast.c
f32-gemm-5x16-minmax-avx512f-broadcast.c
f32-gemm-5x16-minmax-fma3-broadcast.c
f32-gemm-5x16-minmax-neon-lane-ld128.c
f32-gemm-5x16s4-minmax-fma3-broadcast.c
f32-gemm-5x32-minmax-avx512f-broadcast.c
f32-gemm-5x64-minmax-avx512f-broadcast.c
f32-gemm-5x8-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-5x8-minmax-asm-aarch64-neonfma-cortex-a75-prfm.S
f32-gemm-5x8-minmax-asm-aarch64-neonfma-cortex-a75.S
f32-gemm-5x8-minmax-avx-broadcast.c
f32-gemm-5x8-minmax-fma3-broadcast.c
f32-gemm-5x8-minmax-neon-lane-ld64.c
f32-gemm-5x8-minmax-sse-dup.c
f32-gemm-5x8-minmax-sse-load1.c
f32-gemm-5x8-minmax-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-5x8-minmax-wasmrelaxedsimd-fma-splat.c
f32-gemm-5x8-minmax-wasmrelaxedsimd-loadsplat.c
f32-gemm-5x8-minmax-wasmrelaxedsimd-splat.c
f32-gemm-5x8-minmax-wasmsimd-arm-loadsplat.c
f32-gemm-5x8-minmax-wasmsimd-arm-splat.c
f32-gemm-5x8-minmax-wasmsimd-x86-loadsplat.c
f32-gemm-5x8-minmax-wasmsimd-x86-splat.c
f32-gemm-5x8-relu-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-5x8-relu-wasmrelaxedsimd-fma-splat.c
f32-gemm-5x8-relu-wasmsimd-loadsplat.c
f32-gemm-5x8-relu-wasmsimd-splat.c
f32-gemm-5x8-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-5x8-wasmrelaxedsimd-fma-splat.c
f32-gemm-5x8-wasmsimd-loadsplat.c
f32-gemm-5x8-wasmsimd-splat.c
f32-gemm-5x8s4-minmax-sse.c
f32-gemm-5x8s4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-5x8s4-minmax-wasmrelaxedsimd.c
f32-gemm-5x8s4-minmax-wasmsimd-arm.c
f32-gemm-5x8s4-minmax-wasmsimd-x86.c
f32-gemm-5x8s4-relu-wasmrelaxedsimd-fma.c
f32-gemm-5x8s4-relu-wasmsimd.c
f32-gemm-5x8s4-wasmrelaxedsimd-fma.c
f32-gemm-5x8s4-wasmsimd.c
f32-gemm-6x16-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-6x16-minmax-avx-broadcast.c
f32-gemm-6x16-minmax-avx512f-broadcast.c
f32-gemm-6x16-minmax-fma3-broadcast.c
f32-gemm-6x16-minmax-neon-lane-ld128.c
f32-gemm-6x16s4-minmax-fma3-broadcast.c
f32-gemm-6x2-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-6x2-minmax-neon-lane-ld64.c
f32-gemm-6x2c4-minmax-sse.c
f32-gemm-6x32-minmax-avx512f-broadcast.c
f32-gemm-6x64-minmax-avx512f-broadcast.c
f32-gemm-6x8-minmax-aarch64-neonfma-lane-ld128.c
f32-gemm-6x8-minmax-aarch64-neonfma-lane-ld64.c
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a53-prfm.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a53.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a55.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a73.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a75-prfm.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-cortex-a75.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-6x8-minmax-asm-aarch64-neonfma-ld64.S
f32-gemm-6x8-minmax-avx-broadcast.c
f32-gemm-6x8-minmax-fma3-broadcast.c
f32-gemm-6x8-minmax-neon-dup-ld128.c
f32-gemm-6x8-minmax-neon-dup-ld64.c
f32-gemm-6x8-minmax-neon-lane-ld128.c
f32-gemm-6x8-minmax-neon-lane-ld64.c
f32-gemm-6x8-minmax-neonfma-dup-ld128.c
f32-gemm-6x8-minmax-neonfma-dup-ld64.c
f32-gemm-6x8-minmax-sse-dup.c
f32-gemm-6x8-minmax-sse-load1.c
f32-gemm-6x8-minmax-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-6x8-minmax-wasmrelaxedsimd-fma-splat.c
f32-gemm-6x8-minmax-wasmrelaxedsimd-loadsplat.c
f32-gemm-6x8-minmax-wasmrelaxedsimd-splat.c
f32-gemm-6x8-minmax-wasmsimd-arm-loadsplat.c
f32-gemm-6x8-minmax-wasmsimd-arm-splat.c
f32-gemm-6x8-minmax-wasmsimd-x86-loadsplat.c
f32-gemm-6x8-minmax-wasmsimd-x86-splat.c
f32-gemm-6x8-relu-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-6x8-relu-wasmrelaxedsimd-fma-splat.c
f32-gemm-6x8-relu-wasmsimd-loadsplat.c
f32-gemm-6x8-relu-wasmsimd-splat.c
f32-gemm-6x8-wasmrelaxedsimd-fma-loadsplat.c
f32-gemm-6x8-wasmrelaxedsimd-fma-splat.c
f32-gemm-6x8-wasmsimd-loadsplat.c
f32-gemm-6x8-wasmsimd-splat.c
f32-gemm-6x8s4-minmax-neon.c
f32-gemm-6x8s4-minmax-neonfma.c
f32-gemm-6x8s4-minmax-sse.c
f32-gemm-6x8s4-minmax-wasmrelaxedsimd-fma.c
f32-gemm-6x8s4-minmax-wasmrelaxedsimd.c
f32-gemm-6x8s4-minmax-wasmsimd-arm.c
f32-gemm-6x8s4-minmax-wasmsimd-x86.c
f32-gemm-6x8s4-relu-wasmrelaxedsimd-fma.c
f32-gemm-6x8s4-relu-wasmsimd.c
f32-gemm-6x8s4-wasmrelaxedsimd-fma.c
f32-gemm-6x8s4-wasmsimd.c
f32-gemm-7x16-minmax-avx512f-broadcast.c
f32-gemm-7x32-minmax-avx512f-broadcast.c
f32-gemm-7x4v-minmax-rvv.c
f32-gemm-7x4v-relu-rvv.c
f32-gemm-7x4v-rvv.c
f32-gemm-7x64-minmax-avx512f-broadcast.c
f32-gemm-7x64-minmax-hvx-broadcast.c
f32-gemm-7x8-minmax-avx-broadcast.c
f32-gemm-7x8-minmax-fma3-broadcast.c
f32-gemm-8x16-minmax-avx512f-broadcast.c
f32-gemm-8x32-minmax-avx512f-broadcast.c
f32-gemm-8x32-minmax-hvx-broadcast.c
f32-gemm-8x64-minmax-avx512f-broadcast.c
f32-gemm-8x8-minmax-fma3-broadcast.c
f32-gemm-8x8s4-minmax-neon.c
f32-gemm-8x8s4-minmax-neonfma.c
f32-gemm-9x16-minmax-avx512f-broadcast.c
f32-gemm-9x32-minmax-avx512f-broadcast.c
f32-gemm-9x64-minmax-avx512f-broadcast.c
f32-gemm-goi-1x8-minmax-asm-aarch64-neonfma-ld128-prfm.S
f32-gemm-goi-1x8-minmax-asm-aarch64-neonfma-ld128.S
f32-gemm-goi-4x8-minmax-asm-aarch64-neonfma-ld128.S