JitArm64: Use AArch64 imm masks in rlwimix slow case

All valid PPC imm masks (except for all zeroes and all ones) are also
valid AArch64 imm masks. This lets us optimize things a little.

Note that because I'm now ANDing rS before rotating it, its AND mask
is rotated left. All AArch64 imm masks can be rotated by any amount and
still be valid AArch64 imm masks.

1 files changed, 4 insertions, 5 deletions

diff --git a/Source/Core/Core/PowerPC/JitArm64/JitArm64_Integer.cpp b/Source/Core/Core/PowerPC/JitArm64/JitArm64_Integer.cpp
index 76f771abe5..51f6c836fb 100644
--- a/Source/Core/Core/PowerPC/JitArm64/JitArm64_Integer.cpp
+++ b/Source/Core/Core/PowerPC/JitArm64/JitArm64_Integer.cpp
@@ -2113,12 +2113,11 @@ void JitArm64::rlwimix(UGeckoInstruction inst)
       gpr.BindToRegister(a, true);
       ARM64Reg RA = gpr.R(a);
       auto WA = gpr.GetScopedReg();
-      auto WB = a == s ? gpr.GetScopedReg() : Arm64GPRCache::ScopedARM64Reg(RA);
+      const u32 inverted_mask = ~mask;
 
-      MOVI2R(WA, mask);
-      BIC(WB, RA, WA);
-      AND(WA, WA, gpr.R(s), ArithOption(gpr.R(s), ShiftType::ROR, rot_dist));
-      ORR(RA, WB, WA);
+      AND(WA, gpr.R(s), LogicalImm(std::rotl(mask, rot_dist), GPRSize::B32));
+      AND(RA, RA, LogicalImm(inverted_mask, GPRSize::B32));
+      ORR(RA, RA, WA, ArithOption(WA, ShiftType::ROR, rot_dist));
     }
 
     if (inst.Rc)