A scalar result (an FP operation, a scalar load, FMOV, a compare, a conversion, a 64-bit vector operation) was assigned
to the register as a zero-extended 128-bit integer, which the compiler writes as two 8-byte stores, and INS and a
single-lane load wrote their lane alone. The next 16-byte load of the register then cannot take its value from the
store buffer and waits until the stores have left it.
Every such write now builds the whole value in a vector register and stores it once (runtime/simd.h): VSET puts a
scalar in the low bits with zero above it, VSET128 writes a 128-bit value built in an integer, and VINS loads the
register, replaces one lane and stores all of it. VINS passes the value through an empty asm statement, without which
the compiler turns the load, the insert and the store back into a store of the lane.
In the 360 guest functions a play profile sampled, stores of a part of a V register fall from 64322 to 4 and whole
stores rise from 10932 to 43665; the four left copy a 16-byte guest load that the compiler itself splits because the
memory was just written in halves. Host instructions fall from 1448075 to 1427163 and stores to the Cpu from 177160 to
145566; its loads rise from 141090 to 143521, as an insert loads the register it changes.
The lifted text of FP and SIMD code changes with this, so those files are compiled again.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
Each file that contains copied code names its copyright holder and license and points at THIRD_PARTY_NOTICES.md; zlib code keeps its full notice and the mark that it was altered. Comments and probe text only.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
