src/f16-avgpool/f16-avgpool-9p8x-minmax-f16c-c8.c src/f16-avgpool/f16-avgpool-9x-minmax-f16c-c8.c src/f16-dwconv/gen/f16-dwconv-25p8c-minmax-fma3-acc2.c src/f16-dwconv/gen/f16-dwconv-3p16c-minmax-fma3.c src/f16-dwconv/gen/f16-dwconv-4p16c-minmax-fma3.c src/f16-dwconv/gen/f16-dwconv-9p16c-minmax-fma3.c src/f16-f32-vcvt/gen/f16-f32-vcvt-avx-int16-u16.c src/f16-f32-vcvt/gen/f16-f32-vcvt-avx512skx-u16.c src/f16-f32-vcvt/gen/f16-f32-vcvt-f16c-u16.c src/f16-f32-vcvt/gen/f16-f32-vcvt-scalar-u1.c src/f16-f32-vcvt/gen/f16-f32-vcvt-scalar-u4.c src/f16-f32-vcvt/gen/f16-f32-vcvt-sse2-int16-u32.c src/f16-f32-vcvt/gen/f16-f32-vcvt-sse41-int16-u16.c src/f16-f32acc-gemm/gen/f16-f32acc-gemm-1x16-minmax-avx2-broadcast.c src/f16-f32acc-gemm/gen/f16-f32acc-gemm-4x16-minmax-avx2-broadcast.c src/f16-f32acc-igemm/gen/f16-f32acc-igemm-1x16-minmax-avx2-broadcast.c src/f16-f32acc-igemm/gen/f16-f32acc-igemm-4x16-minmax-avx2-broadcast.c src/f16-f32acc-rdsum/gen/f16-f32acc-rdsum-7p7x-avx512skx-c64.c src/f16-f32acc-rdsum/gen/f16-f32acc-rdsum-7p7x-f16c-c32.c src/f16-f32acc-rsum/gen/f16-f32acc-rsum-avx512skx-u64-acc4.c src/f16-f32acc-rsum/gen/f16-f32acc-rsum-f16c-u32-acc4.c src/f16-ibilinear/gen/f16-ibilinear-fma3-c8.c src/f16-maxpool/f16-maxpool-9p8x-minmax-f16c-c8.c src/f16-pavgpool/f16-pavgpool-9p8x-minmax-avx2-c8.c src/f16-pavgpool/f16-pavgpool-9x-minmax-avx2-c8.c src/f16-qs8-vcvt/gen/f16-qs8-vcvt-scalar-imagic-u4.c src/f16-qu8-vcvt/gen/f16-qu8-vcvt-scalar-imagic-u4.c src/f16-raddstoreexpminusmax/gen/f16-raddstoreexpminusmax-avx2-rr1-p2-u32.c src/f16-rminmax/f16-rmax-f16c-u32.c src/f16-rminmax/gen/f16-rmax-avx512skx-u64-acc4.c src/f16-rminmax/gen/f16-rmax-scalar-u2-acc2.c src/f16-rminmax/gen/f16-rminmax-avx512skx-u64-acc4.c src/f16-rminmax/gen/f16-rminmax-scalar-u2-acc2.c src/f16-vbinary/gen/f16-vadd-f16c-u16.c src/f16-vbinary/gen/f16-vaddc-f16c-u16.c src/f16-vbinary/gen/f16-vdiv-f16c-u8.c src/f16-vbinary/gen/f16-vdivc-f16c-u8.c src/f16-vbinary/gen/f16-vmax-f16c-u16.c src/f16-vbinary/gen/f16-vmaxc-f16c-u16.c src/f16-vbinary/gen/f16-vmin-f16c-u16.c src/f16-vbinary/gen/f16-vminc-f16c-u16.c src/f16-vbinary/gen/f16-vmul-f16c-u16.c src/f16-vbinary/gen/f16-vmulc-f16c-u16.c src/f16-vbinary/gen/f16-vprelu-f16c-u16.c src/f16-vbinary/gen/f16-vpreluc-f16c-u16.c src/f16-vbinary/gen/f16-vrdivc-f16c-u8.c src/f16-vbinary/gen/f16-vrpreluc-f16c-u16.c src/f16-vbinary/gen/f16-vrsubc-f16c-u16.c src/f16-vbinary/gen/f16-vsqrdiff-f16c-u16.c src/f16-vbinary/gen/f16-vsqrdiffc-f16c-u16.c src/f16-vbinary/gen/f16-vsub-f16c-u16.c src/f16-vbinary/gen/f16-vsubc-f16c-u16.c src/f16-vclamp/gen/f16-vclamp-f16c-u16.c src/f16-velu/gen/f16-velu-avx2-rr1-p3-u16.c src/f16-vhswish/gen/f16-vhswish-f16c-u16.c src/f16-vlrelu/gen/f16-vlrelu-f16c-u16.c src/f16-vmulcaddc/gen/f16-vmulcaddc-c8-minmax-fma3-2x.c src/f16-vrnd/gen/f16-vrndd-f16c-u16.c src/f16-vrnd/gen/f16-vrndne-f16c-u16.c src/f16-vrnd/gen/f16-vrndu-f16c-u16.c src/f16-vrnd/gen/f16-vrndz-f16c-u16.c src/f16-vrsqrt/gen/f16-vrsqrt-f16c-rsqrt-u32.c src/f16-vsigmoid/gen/f16-vsigmoid-avx2-rr1-p2-rcp-u32.c src/f16-vsqrt/gen/f16-vsqrt-f16c-rsqrt-u32.c src/f16-vtanh/gen/f16-vtanh-f16c-expm1minus-rr1-p3h2ts-rcp-u24.c src/f16-vtanh/gen/f16-vtanh-fma3-polynomial-p19h9t2-u32.c src/f16-vunary/gen/f16-vabs-sse2-u16.c src/f16-vunary/gen/f16-vneg-sse2-u16.c src/f16-vunary/gen/f16-vsqr-f16c-u16.c src/f32-argmaxpool/f32-argmaxpool-4x-scalar-c1.c src/f32-argmaxpool/f32-argmaxpool-4x-sse2-c4.c src/f32-argmaxpool/f32-argmaxpool-9p8x-scalar-c1.c src/f32-argmaxpool/f32-argmaxpool-9p8x-sse2-c4.c src/f32-argmaxpool/f32-argmaxpool-9x-scalar-c1.c src/f32-argmaxpool/f32-argmaxpool-9x-sse2-c4.c src/f32-avgpool/f32-avgpool-9p8x-minmax-scalar-c1.c src/f32-avgpool/f32-avgpool-9p8x-minmax-sse-c4.c src/f32-avgpool/f32-avgpool-9x-minmax-scalar-c1.c src/f32-avgpool/f32-avgpool-9x-minmax-sse-c4.c src/f32-conv-hwc2chw/f32-conv-hwc2chw-3x3s2p1c3x4-scalar-1x1.c src/f32-conv-hwc2chw/f32-conv-hwc2chw-3x3s2p1c3x4-sse-2x2.c src/f32-dwconv/gen/f32-dwconv-25p16c-minmax-avx512f.c src/f32-dwconv/gen/f32-dwconv-25p1c-minmax-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-25p1c-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-avx.c src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-fma3.c src/f32-dwconv/gen/f32-dwconv-25p8c-minmax-sse.c src/f32-dwconv/gen/f32-dwconv-2f2m2l4c1s1r-minmax-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-avx.c src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-avx512f.c src/f32-dwconv/gen/f32-dwconv-3p16c-minmax-fma3.c src/f32-dwconv/gen/f32-dwconv-3p1c-minmax-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-3p1c-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-3p8c-minmax-sse.c src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-avx.c src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-avx512f.c src/f32-dwconv/gen/f32-dwconv-4p16c-minmax-fma3.c src/f32-dwconv/gen/f32-dwconv-4p1c-minmax-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-4p1c-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-4p8c-minmax-sse.c src/f32-dwconv/gen/f32-dwconv-5f5m5l32c16s1r-minmax-avx512f.c src/f32-dwconv/gen/f32-dwconv-5f5m5l8c8s4r-minmax-fma3.c src/f32-dwconv/gen/f32-dwconv-6f6m7l8c8s4r-minmax-avx.c src/f32-dwconv/gen/f32-dwconv-8f8m9l16c4s4r-minmax-sse.c src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-avx.c src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-avx512f.c src/f32-dwconv/gen/f32-dwconv-9p16c-minmax-fma3.c src/f32-dwconv/gen/f32-dwconv-9p1c-minmax-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-9p1c-scalar-acc2.c src/f32-dwconv/gen/f32-dwconv-9p8c-minmax-sse.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-scalar-2x1-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-scalar-4x1.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-sse-2x4-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3p1-minmax-ssse3-2x4-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-scalar-1x1-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-scalar-2x1-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-3x3s2p1-minmax-sse-1x4-acc3.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-scalar-1x1-acc5.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-scalar-2x1-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5p2-minmax-sse-4x4.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-scalar-1x1-acc5.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-scalar-2x1-acc2.c src/f32-dwconv2d-chw/gen/f32-dwconv2d-chw-5x5s2p2-minmax-sse-2x4.c src/f32-f16-vcvt/gen/f32-f16-vcvt-avx-u24.c src/f32-f16-vcvt/gen/f32-f16-vcvt-avx512skx-u16.c src/f32-f16-vcvt/gen/f32-f16-vcvt-f16c-u16.c src/f32-f16-vcvt/gen/f32-f16-vcvt-scalar-bitcast-u4.c src/f32-f16-vcvt/gen/f32-f16-vcvt-scalar-fabsf-u2.c src/f32-f16-vcvt/gen/f32-f16-vcvt-sse2-u16.c src/f32-f16-vcvt/gen/f32-f16-vcvt-sse41-u8.c src/f32-gemm/gen/f32-gemm-1x16-minmax-avx-broadcast.c src/f32-gemm/gen/f32-gemm-1x16-minmax-fma3-broadcast.c src/f32-gemm/gen/f32-gemm-1x16s4-minmax-fma3-broadcast.c src/f32-gemm/gen/f32-gemm-1x32-minmax-avx512f-broadcast.c src/f32-gemm/gen/f32-gemm-1x4-minmax-scalar.c src/f32-gemm/gen/f32-gemm-1x4-relu-scalar.c src/f32-gemm/gen/f32-gemm-1x4-scalar.c src/f32-gemm/gen/f32-gemm-1x8-minmax-sse-load1.c src/f32-gemm/gen/f32-gemm-2x4-minmax-scalar.c src/f32-gemm/gen/f32-gemm-2x4-relu-scalar.c src/f32-gemm/gen/f32-gemm-2x4-scalar.c src/f32-gemm/gen/f32-gemm-4x16s4-minmax-fma3-broadcast.c src/f32-gemm/gen/f32-gemm-4x2-minmax-scalar.c src/f32-gemm/gen/f32-gemm-4x2-scalar.c src/f32-gemm/gen/f32-gemm-4x2c4-minmax-sse.c src/f32-gemm/gen/f32-gemm-4x4-minmax-scalar.c src/f32-gemm/gen/f32-gemm-4x4-relu-scalar.c src/f32-gemm/gen/f32-gemm-4x4-scalar.c src/f32-gemm/gen/f32-gemm-4x8-minmax-sse-load1.c src/f32-gemm/gen/f32-gemm-5x16-minmax-avx-broadcast.c src/f32-gemm/gen/f32-gemm-5x16-minmax-fma3-broadcast.c src/f32-gemm/gen/f32-gemm-7x32-minmax-avx512f-broadcast.c src/f32-ibilinear-chw/gen/f32-ibilinear-chw-scalar-p4.c src/f32-ibilinear-chw/gen/f32-ibilinear-chw-sse-p8.c src/f32-ibilinear/gen/f32-ibilinear-scalar-c2.c src/f32-ibilinear/gen/f32-ibilinear-sse-c8.c src/f32-igemm/gen/f32-igemm-1x16-minmax-avx-broadcast.c src/f32-igemm/gen/f32-igemm-1x16-minmax-fma3-broadcast.c src/f32-igemm/gen/f32-igemm-1x16s4-minmax-fma3-broadcast.c src/f32-igemm/gen/f32-igemm-1x32-minmax-avx512f-broadcast.c src/f32-igemm/gen/f32-igemm-1x4-minmax-scalar.c src/f32-igemm/gen/f32-igemm-1x4-relu-scalar.c src/f32-igemm/gen/f32-igemm-1x4-scalar.c src/f32-igemm/gen/f32-igemm-1x8-minmax-sse-load1.c src/f32-igemm/gen/f32-igemm-2x4-minmax-scalar.c src/f32-igemm/gen/f32-igemm-2x4-relu-scalar.c src/f32-igemm/gen/f32-igemm-2x4-scalar.c src/f32-igemm/gen/f32-igemm-4x16s4-minmax-fma3-broadcast.c src/f32-igemm/gen/f32-igemm-4x2-minmax-scalar.c src/f32-igemm/gen/f32-igemm-4x2-scalar.c src/f32-igemm/gen/f32-igemm-4x2c4-minmax-sse.c src/f32-igemm/gen/f32-igemm-4x4-minmax-scalar.c src/f32-igemm/gen/f32-igemm-4x4-relu-scalar.c src/f32-igemm/gen/f32-igemm-4x4-scalar.c src/f32-igemm/gen/f32-igemm-4x8-minmax-sse-load1.c src/f32-igemm/gen/f32-igemm-5x16-minmax-avx-broadcast.c src/f32-igemm/gen/f32-igemm-5x16-minmax-fma3-broadcast-prfm.c src/f32-igemm/gen/f32-igemm-7x32-minmax-avx512f-broadcast.c src/f32-maxpool/f32-maxpool-9p8x-minmax-scalar-c1.c src/f32-maxpool/f32-maxpool-9p8x-minmax-sse-c4.c src/f32-pavgpool/f32-pavgpool-9p8x-minmax-scalar-c1.c src/f32-pavgpool/f32-pavgpool-9p8x-minmax-sse-c4.c src/f32-pavgpool/f32-pavgpool-9x-minmax-scalar-c1.c src/f32-pavgpool/f32-pavgpool-9x-minmax-sse-c4.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-avx-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-avx2-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x16-minmax-fma3-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x4-minmax-scalar.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-1x8-minmax-sse41-dup.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-avx-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-avx2-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-3x16-minmax-fma3-broadcast.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-4x4-minmax-scalar.c src/f32-qc4w-gemm/gen/f32-qc4w-gemm-4x8-minmax-sse41-dup.c src/f32-qc8w-gemm/gen/f32-qc4w-gemm-1x32-minmax-avx512skx-broadcast.c src/f32-qc8w-gemm/gen/f32-qc4w-gemm-7x32-minmax-avx512skx-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-avx-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-avx2-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x16-minmax-fma3-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x32-minmax-avx512skx-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x4-minmax-scalar.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-1x8-minmax-sse41-dup.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-4x4-minmax-scalar.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-4x8-minmax-sse41-dup.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-avx-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-avx2-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-5x16-minmax-fma3-broadcast.c src/f32-qc8w-gemm/gen/f32-qc8w-gemm-7x32-minmax-avx512skx-broadcast.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx-u32.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx2-u64.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-avx512skx-u128.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-imagic-u1.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-imagic-u4.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-scalar-lrintf-u4.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-sse2-u32.c src/f32-qs8-vcvt/gen/f32-qs8-vcvt-sse41-u32.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx-u32.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx2-u64.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-avx512skx-u128.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-imagic-u1.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-imagic-u4.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-scalar-lrintf-u4.c src/f32-qu8-vcvt/gen/f32-qu8-vcvt-sse2-u32.c src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-avx2-rr2-p5-u32-acc2.c src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-avx512f-rr2-p5-u64-acc2.c src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-scalar-rr2-p5-u4-acc2.c src/f32-raddstoreexpminusmax/gen/f32-raddstoreexpminusmax-sse2-rr2-p5-u16-acc2.c src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-avx-c32.c src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-avx512f-c64.c src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-scalar.c src/f32-rdsum/gen/f32-rdsum-7p7x-minmax-sse-c16.c src/f32-rminmax/gen/f32-rmax-avx-u32-acc4.c src/f32-rminmax/gen/f32-rmax-avx512f-u64-acc4.c src/f32-rminmax/gen/f32-rmax-scalar-u4-acc4.c src/f32-rminmax/gen/f32-rmax-sse-u16-acc4.c src/f32-rminmax/gen/f32-rminmax-avx-u32-acc4.c src/f32-rminmax/gen/f32-rminmax-avx512f-u64-acc4.c src/f32-rminmax/gen/f32-rminmax-scalar-u4-acc4.c src/f32-rminmax/gen/f32-rminmax-sse-u16-acc4.c src/f32-rsum/gen/f32-rsum-avx-u32-acc4.c src/f32-rsum/gen/f32-rsum-avx512f-u64-acc4.c src/f32-rsum/gen/f32-rsum-scalar-u4-acc4.c src/f32-rsum/gen/f32-rsum-sse-u16-acc4.c src/f32-spmm/gen/f32-spmm-32x1-minmax-sse.c src/f32-spmm/gen/f32-spmm-8x1-minmax-scalar.c src/f32-spmm/gen/f32-spmm-8x2-minmax-scalar.c src/f32-spmm/gen/f32-spmm-8x4-minmax-scalar.c src/f32-vbinary/gen/f32-vadd-avx-u16.c src/f32-vbinary/gen/f32-vadd-avx512f-u32.c src/f32-vbinary/gen/f32-vadd-scalar-u8.c src/f32-vbinary/gen/f32-vadd-sse-u8.c src/f32-vbinary/gen/f32-vaddc-avx-u16.c src/f32-vbinary/gen/f32-vaddc-avx512f-u32.c src/f32-vbinary/gen/f32-vaddc-scalar-u8.c src/f32-vbinary/gen/f32-vaddc-sse-u8.c src/f32-vbinary/gen/f32-vdiv-avx-u16.c src/f32-vbinary/gen/f32-vdiv-avx512f-u32.c src/f32-vbinary/gen/f32-vdiv-scalar-u2.c src/f32-vbinary/gen/f32-vdiv-sse-u8.c src/f32-vbinary/gen/f32-vdivc-avx-u16.c src/f32-vbinary/gen/f32-vdivc-avx512f-u32.c src/f32-vbinary/gen/f32-vdivc-scalar-u2.c src/f32-vbinary/gen/f32-vdivc-sse-u8.c src/f32-vbinary/gen/f32-vmax-avx-u16.c src/f32-vbinary/gen/f32-vmax-avx512f-u32.c src/f32-vbinary/gen/f32-vmax-scalar-u8.c src/f32-vbinary/gen/f32-vmax-sse-u8.c src/f32-vbinary/gen/f32-vmaxc-avx-u16.c src/f32-vbinary/gen/f32-vmaxc-avx512f-u32.c src/f32-vbinary/gen/f32-vmaxc-scalar-u8.c src/f32-vbinary/gen/f32-vmaxc-sse-u8.c src/f32-vbinary/gen/f32-vmin-avx-u16.c src/f32-vbinary/gen/f32-vmin-avx512f-u32.c src/f32-vbinary/gen/f32-vmin-scalar-u8.c src/f32-vbinary/gen/f32-vmin-sse-u8.c src/f32-vbinary/gen/f32-vminc-avx-u16.c src/f32-vbinary/gen/f32-vminc-avx512f-u32.c src/f32-vbinary/gen/f32-vminc-scalar-u8.c src/f32-vbinary/gen/f32-vminc-sse-u8.c src/f32-vbinary/gen/f32-vmul-avx-u16.c src/f32-vbinary/gen/f32-vmul-avx512f-u32.c src/f32-vbinary/gen/f32-vmul-scalar-u8.c src/f32-vbinary/gen/f32-vmul-sse-u8.c src/f32-vbinary/gen/f32-vmulc-avx-u16.c src/f32-vbinary/gen/f32-vmulc-avx512f-u32.c src/f32-vbinary/gen/f32-vmulc-scalar-u8.c src/f32-vbinary/gen/f32-vmulc-sse-u8.c src/f32-vbinary/gen/f32-vprelu-avx-u16.c src/f32-vbinary/gen/f32-vprelu-avx512f-u32.c src/f32-vbinary/gen/f32-vprelu-scalar-u8.c src/f32-vbinary/gen/f32-vprelu-sse2-u8.c src/f32-vbinary/gen/f32-vpreluc-avx-u16.c src/f32-vbinary/gen/f32-vpreluc-avx512f-u32.c src/f32-vbinary/gen/f32-vpreluc-scalar-u8.c src/f32-vbinary/gen/f32-vpreluc-sse2-u8.c src/f32-vbinary/gen/f32-vrdivc-avx-u16.c src/f32-vbinary/gen/f32-vrdivc-avx512f-u32.c src/f32-vbinary/gen/f32-vrdivc-scalar-u2.c src/f32-vbinary/gen/f32-vrdivc-sse-u8.c src/f32-vbinary/gen/f32-vrpreluc-avx-u16.c src/f32-vbinary/gen/f32-vrpreluc-avx512f-u32.c src/f32-vbinary/gen/f32-vrpreluc-scalar-u8.c src/f32-vbinary/gen/f32-vrpreluc-sse2-u8.c src/f32-vbinary/gen/f32-vrsubc-avx-u16.c src/f32-vbinary/gen/f32-vrsubc-avx512f-u32.c src/f32-vbinary/gen/f32-vrsubc-scalar-u8.c src/f32-vbinary/gen/f32-vrsubc-sse-u8.c src/f32-vbinary/gen/f32-vsqrdiff-avx-u16.c src/f32-vbinary/gen/f32-vsqrdiff-avx512f-u32.c src/f32-vbinary/gen/f32-vsqrdiff-scalar-u8.c src/f32-vbinary/gen/f32-vsqrdiff-sse-u8.c src/f32-vbinary/gen/f32-vsqrdiffc-avx-u16.c src/f32-vbinary/gen/f32-vsqrdiffc-avx512f-u32.c src/f32-vbinary/gen/f32-vsqrdiffc-scalar-u8.c src/f32-vbinary/gen/f32-vsqrdiffc-sse-u8.c src/f32-vbinary/gen/f32-vsub-avx-u16.c src/f32-vbinary/gen/f32-vsub-avx512f-u32.c src/f32-vbinary/gen/f32-vsub-scalar-u8.c src/f32-vbinary/gen/f32-vsub-sse-u8.c src/f32-vbinary/gen/f32-vsubc-avx-u16.c src/f32-vbinary/gen/f32-vsubc-avx512f-u32.c src/f32-vbinary/gen/f32-vsubc-scalar-u8.c src/f32-vbinary/gen/f32-vsubc-sse-u8.c src/f32-vclamp/gen/f32-vclamp-avx-u16.c src/f32-vclamp/gen/f32-vclamp-avx512f-u16.c src/f32-vclamp/gen/f32-vclamp-scalar-u4.c src/f32-vclamp/gen/f32-vclamp-sse-u8.c src/f32-vcmul/gen/f32-vcmul-avx512f-u32.c src/f32-vcmul/gen/f32-vcmul-fma3-u16.c src/f32-vcmul/gen/f32-vcmul-scalar-u4.c src/f32-vcmul/gen/f32-vcmul-sse-u8.c src/f32-vcopysign/gen/f32-vcopysign-avx.c src/f32-vcopysign/gen/f32-vcopysign-avx512f.c src/f32-vcopysign/gen/f32-vcopysign-scalar.c src/f32-vcopysign/gen/f32-vcopysign-sse2.c src/f32-vcopysign/gen/f32-vcopysignc-avx.c src/f32-vcopysign/gen/f32-vcopysignc-avx512f.c src/f32-vcopysign/gen/f32-vcopysignc-scalar.c src/f32-vcopysign/gen/f32-vcopysignc-sse2.c src/f32-vcopysign/gen/f32-vrcopysignc-avx.c src/f32-vcopysign/gen/f32-vrcopysignc-avx512f.c src/f32-vcopysign/gen/f32-vrcopysignc-scalar.c src/f32-vcopysign/gen/f32-vrcopysignc-sse2.c src/f32-velu/gen/f32-velu-avx-rr2-lut4-p4-perm-u32.c src/f32-velu/gen/f32-velu-avx2-rr1-lut4-p4-perm-u32.c src/f32-velu/gen/f32-velu-avx512f-rr1-p6-u64.c src/f32-velu/gen/f32-velu-scalar-rr2-lut16-p3-u2.c src/f32-velu/gen/f32-velu-scalar-rr2-lut16-p3-u4.c src/f32-velu/gen/f32-velu-sse2-rr2-lut16-p3-u12.c src/f32-vexp/gen/f32-vexp-scalar-exp.c src/f32-vgelu/gen/f32-vgelu-avx-rational-12-10-div.c src/f32-vgelu/gen/f32-vgelu-avx512f-rational-12-10-nr.c src/f32-vgelu/gen/f32-vgelu-fma3-rational-12-10-div.c src/f32-vgelu/gen/f32-vgelu-scalar-rational-12-10-div.c src/f32-vgelu/gen/f32-vgelu-sse2-rational-12-10-div.c src/f32-vhswish/gen/f32-vhswish-avx-u16.c src/f32-vhswish/gen/f32-vhswish-avx512f-u16.c src/f32-vhswish/gen/f32-vhswish-fma3-u16.c src/f32-vhswish/gen/f32-vhswish-scalar-u4.c src/f32-vhswish/gen/f32-vhswish-sse-u8.c src/f32-vlog/gen/f32-vlog-avx2-rational-3-3-div.c src/f32-vlog/gen/f32-vlog-avx512f-rational-3-3-div.c src/f32-vlog/gen/f32-vlog-fma3-rational-3-3-div.c src/f32-vlog/gen/f32-vlog-scalar-rational-3-3-div.c src/f32-vlog/gen/f32-vlog-sse2-rational-3-3-div.c src/f32-vlrelu/gen/f32-vlrelu-avx-u16.c src/f32-vlrelu/gen/f32-vlrelu-avx512f-u16.c src/f32-vlrelu/gen/f32-vlrelu-scalar-u4.c src/f32-vlrelu/gen/f32-vlrelu-sse-u8.c src/f32-vlrelu/gen/f32-vlrelu-sse41-u8.c src/f32-vmulcaddc/gen/f32-vmulcaddc-c1-minmax-scalar-2x.c src/f32-vmulcaddc/gen/f32-vmulcaddc-c4-minmax-sse-2x.c src/f32-vrelu/gen/f32-vrelu-scalar-u8.c src/f32-vrnd/gen/f32-vrndd-avx-u16.c src/f32-vrnd/gen/f32-vrndd-avx512f-u16.c src/f32-vrnd/gen/f32-vrndd-scalar-libm-u1.c src/f32-vrnd/gen/f32-vrndd-scalar-libm-u4.c src/f32-vrnd/gen/f32-vrndd-sse2-u8.c src/f32-vrnd/gen/f32-vrndd-sse41-u8.c src/f32-vrnd/gen/f32-vrndne-avx-u16.c src/f32-vrnd/gen/f32-vrndne-avx512f-u16.c src/f32-vrnd/gen/f32-vrndne-scalar-libm-u1.c src/f32-vrnd/gen/f32-vrndne-scalar-libm-u4.c src/f32-vrnd/gen/f32-vrndne-sse2-u8.c src/f32-vrnd/gen/f32-vrndne-sse41-u8.c src/f32-vrnd/gen/f32-vrndu-avx-u16.c src/f32-vrnd/gen/f32-vrndu-avx512f-u16.c src/f32-vrnd/gen/f32-vrndu-scalar-libm-u1.c src/f32-vrnd/gen/f32-vrndu-scalar-libm-u4.c src/f32-vrnd/gen/f32-vrndu-sse2-u8.c src/f32-vrnd/gen/f32-vrndu-sse41-u8.c src/f32-vrnd/gen/f32-vrndz-avx-u16.c src/f32-vrnd/gen/f32-vrndz-avx512f-u16.c src/f32-vrnd/gen/f32-vrndz-scalar-libm-u1.c src/f32-vrnd/gen/f32-vrndz-scalar-libm-u4.c src/f32-vrnd/gen/f32-vrndz-sse2-u8.c src/f32-vrnd/gen/f32-vrndz-sse41-u8.c src/f32-vrsqrt/gen/f32-vrsqrt-avx-rsqrt-u16.c src/f32-vrsqrt/gen/f32-vrsqrt-avx512f-rsqrt-u32.c src/f32-vrsqrt/gen/f32-vrsqrt-fma3-rsqrt-u16.c src/f32-vrsqrt/gen/f32-vrsqrt-scalar-rsqrt-u1.c src/f32-vrsqrt/gen/f32-vrsqrt-scalar-rsqrt-u4.c src/f32-vrsqrt/gen/f32-vrsqrt-sse-rsqrt-u8.c src/f32-vsigmoid/gen/f32-vsigmoid-avx-rr2-p5-nr2-u16.c src/f32-vsigmoid/gen/f32-vsigmoid-avx2-rr1-p5-div-u16.c src/f32-vsigmoid/gen/f32-vsigmoid-avx512f-rr2-lut32-p2-perm2-scalef-div-u64.c src/f32-vsigmoid/gen/f32-vsigmoid-scalar-rr2-lut64-p2-div-u2.c src/f32-vsigmoid/gen/f32-vsigmoid-sse2-rr2-lut64-p2-div-u8.c src/f32-vsigmoid/gen/f32-vsigmoid-sse41-rr2-lut64-p2-div-u8.c src/f32-vsqrt/gen/f32-vsqrt-avx-rsqrt-u16.c src/f32-vsqrt/gen/f32-vsqrt-avx512f-rsqrt-u16.c src/f32-vsqrt/gen/f32-vsqrt-fma3-rsqrt-u16.c src/f32-vsqrt/gen/f32-vsqrt-scalar-sqrt-u1.c src/f32-vsqrt/gen/f32-vsqrt-sse-rsqrt-u12.c src/f32-vtanh/gen/f32-vtanh-avx-rational-9-8-div.c src/f32-vtanh/gen/f32-vtanh-avx512f-rational-9-8-nr.c src/f32-vtanh/gen/f32-vtanh-fma3-rational-9-8-div.c src/f32-vtanh/gen/f32-vtanh-scalar-rational-9-8-div.c src/f32-vtanh/gen/f32-vtanh-sse2-rational-9-8-div.c src/f32-vunary/gen/f32-vabs-avx.c src/f32-vunary/gen/f32-vabs-avx512f.c src/f32-vunary/gen/f32-vabs-scalar.c src/f32-vunary/gen/f32-vabs-sse2.c src/f32-vunary/gen/f32-vneg-avx.c src/f32-vunary/gen/f32-vneg-avx512f.c src/f32-vunary/gen/f32-vneg-scalar.c src/f32-vunary/gen/f32-vneg-sse2.c src/f32-vunary/gen/f32-vsqr-avx.c src/f32-vunary/gen/f32-vsqr-avx512f.c src/f32-vunary/gen/f32-vsqr-scalar.c src/f32-vunary/gen/f32-vsqr-sse2.c src/qd8-f16-qb4w-gemm/gen/qd8-f16-qb4w-gemm-1x8c8-minmax-avx2.c src/qd8-f16-qb4w-gemm/gen/qd8-f16-qb4w-gemm-3x8c8-minmax-avx2.c src/qd8-f16-qc4w-gemm/gen/qd8-f16-qc4w-gemm-1x8c8-minmax-avx2-madd-prfm.c src/qd8-f16-qc4w-gemm/gen/qd8-f16-qc4w-gemm-4x8c8-minmax-avx2-madd-prfm.c src/qd8-f16-qc8w-gemm/gen/qd8-f16-qc8w-gemm-1x8c8-minmax-avx2.c src/qd8-f16-qc8w-gemm/gen/qd8-f16-qc8w-gemm-3x8c8-minmax-avx2.c src/qd8-f16-qc8w-igemm/gen/qd8-f16-qc8w-igemm-1x8c8-minmax-avx2.c src/qd8-f16-qc8w-igemm/gen/qd8-f16-qc8w-igemm-3x8c8-minmax-avx2.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4-minmax-scalar.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-avx-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-sse2-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x4c8-minmax-sse41-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-1x8c8-minmax-avx2.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-3x4c8-minmax-sse41-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-3x8c8-minmax-avx2.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4-minmax-scalar.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4c8-minmax-avx-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-4x4c8-minmax-sse2-ld128.c src/qd8-f32-qb4w-gemm/gen/qd8-f32-qb4w-gemm-8x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-14x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512skx-madd-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x16c8-minmax-avx512vnnigfni-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4-minmax-scalar.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4c8-minmax-sse2-ld128.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x4c8-minmax-ssse3-madd.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-1x8c8-minmax-avx2-madd-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4-minmax-scalar.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4c8-minmax-sse2-ld128.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x4c8-minmax-ssse3-madd.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-4x8c8-minmax-avx2-madd-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-8x16c8-minmax-avx512skx-madd-prfm.c src/qd8-f32-qc4w-gemm/gen/qd8-f32-qc4w-gemm-8x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-10x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x16c8-minmax-avx512skx-prfm.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x2-minmax-scalar.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4-minmax-scalar.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4c8-minmax-sse2-ld64.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x4c8-minmax-sse41-ld64.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-1x8c8-minmax-avx2.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-2x2-minmax-scalar.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4-minmax-scalar.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4c8-minmax-sse2-ld64.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x4c8-minmax-sse41-ld64.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-4x8c8-minmax-avx2.c src/qd8-f32-qc8w-gemm/gen/qd8-f32-qc8w-gemm-8x16c8-minmax-avx512skx-prfm.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-10x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x16c8-minmax-avx512skx-prfm.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x16c8-minmax-avx512vnni-prfm.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x2-minmax-scalar.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4-minmax-scalar.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4c8-minmax-sse2-ld64.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x4c8-minmax-sse41-ld64.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-1x8c8-minmax-avx2.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-2x2-minmax-scalar.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4-minmax-scalar.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4c8-minmax-sse2-ld64.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x4c8-minmax-sse41-ld64.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-4x8c8-minmax-avx2.c src/qd8-f32-qc8w-igemm/gen/qd8-f32-qc8w-igemm-8x16c8-minmax-avx512skx-prfm.c src/qs8-dwconv/gen/qs8-dwconv-25p16c-minmax-fp32-avx-mul16-add16.c src/qs8-dwconv/gen/qs8-dwconv-25p16c-minmax-fp32-avx2-mul32.c src/qs8-dwconv/gen/qs8-dwconv-25p1c-minmax-fp32-scalar-fmagic.c src/qs8-dwconv/gen/qs8-dwconv-25p1c-minmax-fp32-scalar-imagic.c src/qs8-dwconv/gen/qs8-dwconv-25p2c-minmax-fp32-scalar-lrintf.c src/qs8-dwconv/gen/qs8-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c src/qs8-dwconv/gen/qs8-dwconv-25p8c-minmax-fp32-sse2-mul16-add16.c src/qs8-dwconv/gen/qs8-dwconv-25p8c-minmax-fp32-sse41-mul16-add16.c src/qs8-dwconv/gen/qs8-dwconv-9p16c-minmax-fp32-avx-mul16-add16.c src/qs8-dwconv/gen/qs8-dwconv-9p16c-minmax-fp32-avx2-mul32.c src/qs8-dwconv/gen/qs8-dwconv-9p1c-minmax-fp32-scalar-fmagic.c src/qs8-dwconv/gen/qs8-dwconv-9p2c-minmax-fp32-scalar-imagic.c src/qs8-dwconv/gen/qs8-dwconv-9p2c-minmax-fp32-scalar-lrintf.c src/qs8-dwconv/gen/qs8-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c src/qs8-dwconv/gen/qs8-dwconv-9p8c-minmax-fp32-sse2-mul16-add16.c src/qs8-dwconv/gen/qs8-dwconv-9p8c-minmax-fp32-sse41-mul16-add16.c src/qs8-f16-vcvt/gen/qs8-f16-vcvt-avx2-u16.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx-u32.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx2-u16.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-avx512skx-u32.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-scalar-u1.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-scalar-u4.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-sse2-u32.c src/qs8-f32-vcvt/gen/qs8-f32-vcvt-sse41-u16.c src/qs8-packw/gen/qs8-packw-x16c8-gemm-goi-scalar.c src/qs8-packw/gen/qs8-packw-x64c4-gemm-goi-scalar.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p16c-minmax-fp32-avx-mul16-add16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p16c-minmax-fp32-avx2-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p1c-minmax-fp32-scalar-fmagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p1c-minmax-fp32-scalar-imagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p2c-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p8c-minmax-fp32-sse2-mul16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-25p8c-minmax-fp32-sse41-mul16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p16c-minmax-fp32-avx-mul16-add16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p16c-minmax-fp32-avx2-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p1c-minmax-fp32-scalar-fmagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p2c-minmax-fp32-scalar-imagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p2c-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p32c-minmax-fp32-avx512skx-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p8c-minmax-fp32-sse2-mul16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-3p8c-minmax-fp32-sse41-mul16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p16c-minmax-fp32-avx-mul16-add16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p16c-minmax-fp32-avx2-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p1c-minmax-fp32-scalar-fmagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p2c-minmax-fp32-scalar-imagic.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p2c-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p8c-minmax-fp32-sse2-mul16.c src/qs8-qc8w-dwconv/gen/qs8-qc8w-dwconv-9p8c-minmax-fp32-sse41-mul16.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x16c8-minmax-fp32-avx512skx-prfm.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x16c8-minmax-fp32-avx512vnni-prfm.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x2-minmax-fp32-scalar-imagic.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-avx-ld128.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-sse2-ld64.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x4c8-minmax-fp32-sse41-ld64.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-1x8c8-minmax-fp32-avx2.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-2x2-minmax-fp32-scalar-imagic.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-2x4c8-minmax-fp32-avx-ld128.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4c8-minmax-fp32-sse2-ld64.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x4c8-minmax-fp32-sse41-ld64.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-3x8c8-minmax-fp32-avx2.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-7x16c8-minmax-fp32-avx512skx-prfm.c src/qs8-qc8w-gemm/gen/qs8-qc8w-gemm-7x16c8-minmax-fp32-avx512vnni-prfm.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x16c8-minmax-avx512vnni-prfm.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x16c8-minmax-fp32-avx512skx-prfm.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x2-minmax-fp32-scalar-imagic.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-avx-ld128.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-sse2-ld64.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x4c8-minmax-fp32-sse41-ld64.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-1x8c8-minmax-fp32-avx2.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-2x2-minmax-fp32-scalar-imagic.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-2x4c8-minmax-fp32-avx-ld128.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4-minmax-fp32-scalar-lrintf.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4c8-minmax-fp32-sse2-ld64.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x4c8-minmax-fp32-sse41-ld64.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-3x8c8-minmax-fp32-avx2.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-7x16c8-minmax-avx512vnni-prfm.c src/qs8-qc8w-igemm/gen/qs8-qc8w-igemm-7x16c8-minmax-fp32-avx512skx-prfm.c src/qs8-qu8-packw/gen/qs8-qu8-packw-x16c8-gemm-goi-scalar.c src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-avx2-c64.c src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-avx512skx-c64.c src/qs8-rdsum/gen/qs8-rdsum-7p7x-minmax-fp32-sse41-c64.c src/qs8-rdsum/gen/qs8-rdsum-minmax-fp32-scalar-u1-acc1.c src/qs8-rsum/gen/qs8-rsum-avx2-u64-acc2.c src/qs8-rsum/gen/qs8-rsum-avx512skx-u128-acc2.c src/qs8-rsum/gen/qs8-rsum-avx512vnni-u128-acc2.c src/qs8-rsum/gen/qs8-rsum-scalar-u4.c src/qs8-rsum/gen/qs8-rsum-ssse3-u32-acc2.c src/qs8-vadd/gen/qs8-vadd-minmax-avx-mul32-ld32-u8.c src/qs8-vadd/gen/qs8-vadd-minmax-avx2-mul32-ld64-u16.c src/qs8-vadd/gen/qs8-vadd-minmax-avx512skx-mul32-ld128-u16.c src/qs8-vadd/gen/qs8-vadd-minmax-scalar-u1.c src/qs8-vadd/gen/qs8-vadd-minmax-scalar-u4.c src/qs8-vadd/gen/qs8-vadd-minmax-sse2-mul16-ld64-u8.c src/qs8-vadd/gen/qs8-vadd-minmax-sse41-mul16-ld64-u8.c src/qs8-vaddc/gen/qs8-vaddc-minmax-avx-mul32-ld32-u8.c src/qs8-vaddc/gen/qs8-vaddc-minmax-avx2-mul32-ld64-u16.c src/qs8-vaddc/gen/qs8-vaddc-minmax-avx512skx-mul32-ld128-u16.c src/qs8-vaddc/gen/qs8-vaddc-minmax-scalar-u1.c src/qs8-vaddc/gen/qs8-vaddc-minmax-scalar-u4.c src/qs8-vaddc/gen/qs8-vaddc-minmax-sse2-mul16-ld64-u8.c src/qs8-vaddc/gen/qs8-vaddc-minmax-sse41-mul16-ld64-u8.c src/qs8-vcvt/gen/qs8-vcvt-avx-u32.c src/qs8-vcvt/gen/qs8-vcvt-avx2-u32.c src/qs8-vcvt/gen/qs8-vcvt-scalar-u1.c src/qs8-vcvt/gen/qs8-vcvt-scalar-u4.c src/qs8-vcvt/gen/qs8-vcvt-sse2-u32.c src/qs8-vcvt/gen/qs8-vcvt-sse41-u32.c src/qs8-vcvt/gen/qs8-vcvt-ssse3-u32.c src/qs8-vlrelu/gen/qs8-vlrelu-avx-u32.c src/qs8-vlrelu/gen/qs8-vlrelu-avx2-u32.c src/qs8-vlrelu/gen/qs8-vlrelu-scalar-andxor-u4.c src/qs8-vlrelu/gen/qs8-vlrelu-scalar-select-u4.c src/qs8-vlrelu/gen/qs8-vlrelu-sse2-u32.c src/qs8-vlrelu/gen/qs8-vlrelu-sse41-u32.c src/qs8-vlrelu/gen/qs8-vlrelu-ssse3-u32.c src/qs8-vmul/gen/qs8-vmul-minmax-fp32-avx-mul16-ld64-u16.c src/qs8-vmul/gen/qs8-vmul-minmax-fp32-scalar-u4.c src/qs8-vmul/gen/qs8-vmul-minmax-fp32-sse2-mul16-ld64-u8.c src/qs8-vmul/gen/qs8-vmul-minmax-fp32-sse41-mul16-ld64-u16.c src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-avx-mul16-ld64-u16.c src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-scalar-u4.c src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-sse2-mul16-ld64-u8.c src/qs8-vmulc/gen/qs8-vmulc-minmax-fp32-sse41-mul16-ld64-u16.c src/qu8-avgpool/qu8-avgpool-9p8x-minmax-fp32-scalar-imagic-c1.c src/qu8-avgpool/qu8-avgpool-9p8x-minmax-fp32-sse2-c8.c src/qu8-avgpool/qu8-avgpool-9x-minmax-fp32-scalar-imagic-c1.c src/qu8-avgpool/qu8-avgpool-9x-minmax-fp32-sse2-c8.c src/qu8-dwconv/gen/qu8-dwconv-25p16c-minmax-fp32-avx-mul16.c src/qu8-dwconv/gen/qu8-dwconv-25p16c-minmax-fp32-avx2-mul32.c src/qu8-dwconv/gen/qu8-dwconv-25p1c-minmax-fp32-scalar-fmagic.c src/qu8-dwconv/gen/qu8-dwconv-25p1c-minmax-fp32-scalar-imagic.c src/qu8-dwconv/gen/qu8-dwconv-25p2c-minmax-fp32-scalar-lrintf.c src/qu8-dwconv/gen/qu8-dwconv-25p32c-minmax-fp32-avx512skx-mul32.c src/qu8-dwconv/gen/qu8-dwconv-25p8c-minmax-fp32-sse2-mul16.c src/qu8-dwconv/gen/qu8-dwconv-25p8c-minmax-fp32-sse41-mul16.c src/qu8-dwconv/gen/qu8-dwconv-9p16c-minmax-fp32-avx-mul16.c src/qu8-dwconv/gen/qu8-dwconv-9p16c-minmax-fp32-avx2-mul32.c src/qu8-dwconv/gen/qu8-dwconv-9p1c-minmax-fp32-scalar-fmagic.c src/qu8-dwconv/gen/qu8-dwconv-9p2c-minmax-fp32-scalar-imagic.c src/qu8-dwconv/gen/qu8-dwconv-9p2c-minmax-fp32-scalar-lrintf.c src/qu8-dwconv/gen/qu8-dwconv-9p32c-minmax-fp32-avx512skx-mul32.c src/qu8-dwconv/gen/qu8-dwconv-9p8c-minmax-fp32-sse2-mul16.c src/qu8-dwconv/gen/qu8-dwconv-9p8c-minmax-fp32-sse41-mul16.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx-u32.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx2-u16.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-avx512skx-u32.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-scalar-u1.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-scalar-u4.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-sse2-u32.c src/qu8-f32-vcvt/gen/qu8-f32-vcvt-sse41-u16.c src/qu8-gemm/gen/qu8-gemm-1x16c8-minmax-fp32-avx512skx-prfm.c src/qu8-gemm/gen/qu8-gemm-1x2-minmax-fp32-scalar-imagic.c src/qu8-gemm/gen/qu8-gemm-1x4-minmax-fp32-scalar-lrintf.c src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-avx-ld128.c src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-sse2-ld64.c src/qu8-gemm/gen/qu8-gemm-1x4c8-minmax-fp32-sse41-ld64.c src/qu8-gemm/gen/qu8-gemm-1x8c8-minmax-fp32-avx2.c src/qu8-gemm/gen/qu8-gemm-2x2-minmax-fp32-scalar-imagic.c src/qu8-gemm/gen/qu8-gemm-2x4c8-minmax-fp32-avx-ld128.c src/qu8-gemm/gen/qu8-gemm-3x4-minmax-fp32-scalar-lrintf.c src/qu8-gemm/gen/qu8-gemm-3x4c8-minmax-fp32-sse2-ld64.c src/qu8-gemm/gen/qu8-gemm-3x4c8-minmax-fp32-sse41-ld64.c src/qu8-gemm/gen/qu8-gemm-3x8c8-minmax-fp32-avx2.c src/qu8-gemm/gen/qu8-gemm-7x16c8-minmax-fp32-avx512skx-prfm.c src/qu8-igemm/gen/qu8-igemm-1x16c8-minmax-fp32-avx512skx-prfm.c src/qu8-igemm/gen/qu8-igemm-1x2-minmax-fp32-scalar-imagic.c src/qu8-igemm/gen/qu8-igemm-1x4-minmax-fp32-scalar-lrintf.c src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-avx-ld128.c src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-sse2-ld64.c src/qu8-igemm/gen/qu8-igemm-1x4c8-minmax-fp32-sse41-ld64.c src/qu8-igemm/gen/qu8-igemm-1x8c8-minmax-fp32-avx2.c src/qu8-igemm/gen/qu8-igemm-2x2-minmax-fp32-scalar-imagic.c src/qu8-igemm/gen/qu8-igemm-2x4c8-minmax-fp32-avx-ld128.c src/qu8-igemm/gen/qu8-igemm-3x4-minmax-fp32-scalar-lrintf.c src/qu8-igemm/gen/qu8-igemm-3x4c8-minmax-fp32-sse2-ld64.c src/qu8-igemm/gen/qu8-igemm-3x4c8-minmax-fp32-sse41-ld64.c src/qu8-igemm/gen/qu8-igemm-3x8c8-minmax-fp32-avx2.c src/qu8-igemm/gen/qu8-igemm-7x16c8-minmax-fp32-avx512skx-prfm.c src/qu8-rdsum/gen/qu8-rdsum-7p7x-ssse3-c64.c src/qu8-rdsum/gen/qu8-rdsum-scalar.c src/qu8-rsum/gen/qu8-rsum-avx2-u64-acc2.c src/qu8-rsum/gen/qu8-rsum-scalar-u4.c src/qu8-rsum/gen/qu8-rsum-sse2-u32-acc2.c src/qu8-vadd/gen/qu8-vadd-minmax-avx-mul32-ld32-u8.c src/qu8-vadd/gen/qu8-vadd-minmax-avx2-mul32-ld64-u16.c src/qu8-vadd/gen/qu8-vadd-minmax-avx512skx-mul32-ld128-u16.c src/qu8-vadd/gen/qu8-vadd-minmax-scalar-u1.c src/qu8-vadd/gen/qu8-vadd-minmax-scalar-u4.c src/qu8-vadd/gen/qu8-vadd-minmax-sse2-mul16-ld64-u8.c src/qu8-vadd/gen/qu8-vadd-minmax-sse41-mul16-ld64-u8.c src/qu8-vaddc/gen/qu8-vaddc-minmax-avx-mul32-ld32-u8.c src/qu8-vaddc/gen/qu8-vaddc-minmax-avx2-mul32-ld64-u16.c src/qu8-vaddc/gen/qu8-vaddc-minmax-avx512skx-mul32-ld128-u16.c src/qu8-vaddc/gen/qu8-vaddc-minmax-scalar-u1.c src/qu8-vaddc/gen/qu8-vaddc-minmax-scalar-u4.c src/qu8-vaddc/gen/qu8-vaddc-minmax-sse2-mul16-ld64-u8.c src/qu8-vaddc/gen/qu8-vaddc-minmax-sse41-mul16-ld64-u8.c src/qu8-vcvt/gen/qu8-vcvt-avx-u32.c src/qu8-vcvt/gen/qu8-vcvt-avx2-u32.c src/qu8-vcvt/gen/qu8-vcvt-scalar-u1.c src/qu8-vcvt/gen/qu8-vcvt-scalar-u4.c src/qu8-vcvt/gen/qu8-vcvt-sse2-u32.c src/qu8-vcvt/gen/qu8-vcvt-sse41-u32.c src/qu8-vcvt/gen/qu8-vcvt-ssse3-u32.c src/qu8-vlrelu/gen/qu8-vlrelu-avx-u32.c src/qu8-vlrelu/gen/qu8-vlrelu-avx2-u32.c src/qu8-vlrelu/gen/qu8-vlrelu-scalar-andxor-u4.c src/qu8-vlrelu/gen/qu8-vlrelu-scalar-select-u4.c src/qu8-vlrelu/gen/qu8-vlrelu-sse2-u32.c src/qu8-vlrelu/gen/qu8-vlrelu-sse41-u32.c src/qu8-vlrelu/gen/qu8-vlrelu-ssse3-u32.c src/qu8-vmul/gen/qu8-vmul-minmax-fp32-avx-mul16-ld64-u16.c src/qu8-vmul/gen/qu8-vmul-minmax-fp32-scalar-u4.c src/qu8-vmul/gen/qu8-vmul-minmax-fp32-sse2-mul16-ld64-u8.c src/qu8-vmul/gen/qu8-vmul-minmax-fp32-sse41-mul16-ld64-u16.c src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-avx-mul16-ld64-u16.c src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-scalar-u4.c src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-sse2-mul16-ld64-u8.c src/qu8-vmulc/gen/qu8-vmulc-minmax-fp32-sse41-mul16-ld64-u16.c src/s32-f32-vcvt/gen/s32-f32-vcvt-avx2.c src/s32-f32-vcvt/gen/s32-f32-vcvt-avx512f.c src/s32-f32-vcvt/gen/s32-f32-vcvt-scalar.c src/s8-ibilinear/gen/s8-ibilinear-scalar-c1.c src/s8-ibilinear/gen/s8-ibilinear-sse2-c8.c src/s8-ibilinear/gen/s8-ibilinear-sse41-c16.c src/s8-maxpool/s8-maxpool-9p8x-minmax-scalar-c1.c src/s8-maxpool/s8-maxpool-9p8x-minmax-sse2-c16.c src/s8-maxpool/s8-maxpool-9p8x-minmax-sse41-c16.c src/s8-vclamp/s8-vclamp-avx2-u128.c src/s8-vclamp/s8-vclamp-avx512skx-u256.c src/s8-vclamp/s8-vclamp-scalar-u4.c src/s8-vclamp/s8-vclamp-sse2-u64.c src/s8-vclamp/s8-vclamp-sse41-u64.c src/u8-ibilinear/gen/u8-ibilinear-scalar-c1.c src/u8-ibilinear/gen/u8-ibilinear-sse2-c8.c src/u8-ibilinear/gen/u8-ibilinear-sse41-c16.c src/u8-lut32norm/u8-lut32norm-scalar.c src/u8-maxpool/u8-maxpool-9p8x-minmax-scalar-c1.c src/u8-maxpool/u8-maxpool-9p8x-minmax-sse2-c16.c src/u8-rmax/u8-rmax-scalar-u2.c src/u8-rmax/u8-rmax-sse2-u16.c src/u8-vclamp/u8-vclamp-avx2-u128.c src/u8-vclamp/u8-vclamp-avx512skx-u256.c src/u8-vclamp/u8-vclamp-scalar-u4.c src/u8-vclamp/u8-vclamp-sse2-u64.c src/x16-packw/gen/x16-packw-x16-gemm-goi-avx2-u16-prfm.c src/x16-packw/gen/x16-packw-x64-gemm-goi-scalar-int-u4.c src/x16-transposec/gen/x16-transposec-16x16-reuse-switch-avx2.c src/x16-transposec/gen/x16-transposec-2x4-scalar-int.c src/x16-transposec/gen/x16-transposec-8x8-reuse-multi-sse2.c src/x24-transposec/gen/x24-transposec-1x2-scalar.c src/x24-transposec/x24-transposec-4x4-ssse3.c src/x32-packw/gen/x32-packw-x16-gemm-gio-avx-u8.c src/x32-packw/gen/x32-packw-x16-gemm-goi-avx-u4.c src/x32-packw/gen/x32-packw-x16s4-gemm-goi-avx-u4.c src/x32-packw/gen/x32-packw-x2-gemm-goi-scalar-float-u4.c src/x32-packw/gen/x32-packw-x2c4-gemm-goi-sse2-u4.c src/x32-packw/gen/x32-packw-x32-gemm-gio-avx512f-u8.c src/x32-packw/gen/x32-packw-x32-gemm-goi-avx512f-u4-prfm.c src/x32-packw/gen/x32-packw-x4-gemm-goi-scalar-float-u4.c src/x32-packw/gen/x32-packw-x8-gemm-goi-sse2-u4.c src/x32-transposec/gen/x32-transposec-2x4-scalar-int.c src/x32-transposec/gen/x32-transposec-8x8-reuse-multi-avx.c src/x32-transposec/x32-transposec-4x4-sse.c src/x32-unpool/x32-unpool-scalar.c src/x32-unpool/x32-unpool-sse2.c src/x32-zip/x32-zip-x2-scalar.c src/x32-zip/x32-zip-x2-sse2.c src/x32-zip/x32-zip-x3-scalar.c src/x32-zip/x32-zip-x3-sse2.c src/x32-zip/x32-zip-x4-scalar.c src/x32-zip/x32-zip-x4-sse2.c src/x32-zip/x32-zip-xm-scalar.c src/x32-zip/x32-zip-xm-sse2.c src/x64-transposec/gen/x64-transposec-2x2-multi-mov-sse2.c src/x64-transposec/gen/x64-transposec-4x2-scalar-int.c src/x64-transposec/gen/x64-transposec-4x4-reuse-multi-avx.c src/x8-lut/gen/x8-lut-avx-u64.c src/x8-lut/gen/x8-lut-avx2-u128.c src/x8-lut/gen/x8-lut-avx512skx-vpshufb-u64.c src/x8-lut/gen/x8-lut-avx512vbmi-vpermx2b-u128.c src/x8-lut/gen/x8-lut-scalar-u4.c src/x8-packq/x8-packq-scalar-f32qp8-u1.c src/x8-packw/gen/x8-packw-x16-gemm-goi-scalar-u2.c src/x8-packw/gen/x8-packw-x32-gemm-goi-scalar-u2.c src/x8-packw/gen/x8-packw-x4-gemm-goi-scalar-u2.c src/x8-packw/gen/x8-packw-x8-gemm-goi-scalar-u2.c src/x8-transposec/gen/x8-transposec-16x16-reuse-mov-sse2.c src/x8-transposec/gen/x8-transposec-2x4-scalar-int.c src/x8-transposec/gen/x8-transposec-32x32-reuse-switch-avx2.c src/x8-zip/x8-zip-x2-scalar.c src/x8-zip/x8-zip-x2-sse2.c src/x8-zip/x8-zip-x3-scalar.c src/x8-zip/x8-zip-x3-sse2.c src/x8-zip/x8-zip-x4-scalar.c src/x8-zip/x8-zip-x4-sse2.c src/x8-zip/x8-zip-xm-scalar.c src/x8-zip/x8-zip-xm-sse2.c src/xx-copy/xx-copy-scalar-memcpy.c src/xx-fill/xx-fill-scalar-u16.c src/xx-fill/xx-fill-sse2-u64.c src/xx-pad/xx-pad-p16-sse2-u16.c src/xx-pad/xx-pad-p4-scalar-u16.c src/xx-transposev/xx-transposev-1x1-scalar-memcpy.c