Switch WASM128_GENERIC to unroll 4 with matching ncopy/tcopy and TRMM 4x4 so packing width stays consistent. Use relaxed SIMD madd in the inner loop when compiled with -mrelaxed-simd. Signed-off-by: Julien Jerphanion <git@jjerphan.xyz>
2 lines
40 B
Makefile
2 lines
40 B
Makefile
CCOMMON_OPT += -msimd128 -mrelaxed-simd
|