AMX int8/bf16 tile GEMM — enable, fix 5 bugs, optimize (0→197 GMAC/s) + vertical-SIMD primitives #550

Job	Run time
tier4-avx512-check	28s
nostd/thumbv6m-none-eabi/stable	29s
format/stable	22s
clippy/1.95.0	35s
hpc-stream-parallel/rayon	1m 29s
Pass MSRV values to other jobs	3s
native-backend/stable	7m 43s
nightly-simd-polyfill	0s
miri	0s
cargo-careful	0s
docs/nightly	0s
cross_test/${{ matrix.target }}/${{ matrix.rust }}	0s
blas-msrv	54s
tests/1.95.0	11m 19s
tests/stable	10m 42s
tests/beta	11m 5s
conclusion	-1s
	45m 8s

Provide feedback