JIT/AArch64: advertise +i8mm to the LLVM target machine

The PPU/SPU recompilers emit i8mm intrinsics (ummla/smmla, used by the
SPU GBB/GBH gather paths) gated on utils::has_i8mm(). The JIT's MAttrs
list mirrored dotprod/sha3/sve from HWCAP but never added i8mm, and the
resolved -mcpu on Apple silicon is the cortex-a78 fallback (no i8mm), so
the backend aborted with "Cannot select: intrinsic %llvm.aarch64.neon.ummla"
on every game. Mirror i8mm into MAttrs like the other features.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
(cherry picked from commit 52d121fee79cc569c9ac273852edd0e493ae51fc)
This commit is contained in:
Rad0van 2026-06-06 10:30:55 +02:00 committed by Elad
parent 62d32ab45e
commit d25972e196

View File

@ -750,6 +750,15 @@ jit_compiler::jit_compiler(const std::unordered_map<std::string, u64>& _link, co
else
attributes.push_back("-dotprod");
// The recompilers emit i8mm intrinsics (e.g. ummla) gated on utils::has_i8mm().
// The JIT target features must advertise i8mm too, otherwise the backend fails
// with "Cannot select: intrinsic %llvm.aarch64.neon.ummla" whenever the resolved
// -mcpu does not already imply it (e.g. the cortex-a78 fallback on Apple silicon).
if (utils::has_i8mm())
attributes.push_back("+i8mm");
else
attributes.push_back("-i8mm");
if (utils::has_sve())
attributes.push_back("+sve");
else