simd: agnostic gemm_u8_i8 surface, integer-slice-op lift, per-CPU matrix, BF16 AMX wiring #400

Job	Run time
native-backend/stable	7m 46s
hpc-stream-parallel/rayon	1m 19s
tier4-avx512-check	31s
Pass MSRV values to other jobs	3s
nostd/thumbv6m-none-eabi/stable	26s
format/stable	21s
clippy/1.95.0	40s
cross_test/${{ matrix.target }}/${{ matrix.rust }}	0s
miri	0s
nightly-simd-polyfill	0s
docs/nightly	-1s
cargo-careful	-1s
tests/stable	10m 49s
tests/1.95.0	10m 57s
tests/beta	11m 30s
blas-msrv	41s
conclusion	0s
	45m 1s

Provide feedback