add some missing non-square matrix funcs #87

Job	Run time
build_wasi_sdk (Release, 19)	29s
build_wasi_sdk (Release, 20)	27s
build_wasi_sdk (Release, -msimd128, 19)	25s
build_wasi_sdk (Release, -msimd128, 20)	25s
build_wasi_sdk (Debug, 19)	35s
build_wasi_sdk (Debug, 20)	26s
build_wasi_sdk (Debug, -msimd128, 19)	31s
build_wasi_sdk (Debug, -msimd128, 20)	30s
build_wasi_sdk (RelWithDebInfo, 19)	35s
build_wasi_sdk (RelWithDebInfo, 20)	37s
build_wasi_sdk (RelWithDebInfo, -msimd128, 19)	38s
build_wasi_sdk (RelWithDebInfo, -msimd128, 20)	39s
build_wasi_sdk (MinSizeRel, 19)	25s
build_wasi_sdk (MinSizeRel, 20)	32s
build_wasi_sdk (MinSizeRel, -msimd128, 19)	34s
build_wasi_sdk (MinSizeRel, -msimd128, 20)	30s
build_emsdk (Release)	1m 7s
build_emsdk (Release, -msimd128)	1m 18s
build_emsdk (Release, -msse -msse2 -msimd128)	1m 31s
build_emsdk (Release, -msse -msse2 -msse3 -msse4 -msimd128)	1m 12s
build_emsdk (Debug)	1m 10s
build_emsdk (Debug, -msimd128)	1m 13s
build_emsdk (Debug, -msse -msse2 -msimd128)	1m 18s
build_emsdk (Debug, -msse -msse2 -msse3 -msse4 -msimd128)	1m 17s
build_emsdk (RelWithDebInfo)	1m 11s
build_emsdk (RelWithDebInfo, -msimd128)	1m 17s
build_emsdk (RelWithDebInfo, -msse -msse2 -msimd128)	1m 12s
build_emsdk (RelWithDebInfo, -msse -msse2 -msse3 -msse4 -msimd128)	1m 27s
build_emsdk (MinSizeRel)	1m 22s
build_emsdk (MinSizeRel, -msimd128)	1m 16s
build_emsdk (MinSizeRel, -msse -msse2 -msimd128)	1m 29s
build_emsdk (MinSizeRel, -msse -msse2 -msse3 -msse4 -msimd128)	1m 14s
	28m 52s

Provide feedback