Merge pull request #3501 from bylaws/memcpy

FEXCore: Fallback to the memcpy slow path for overlaps within 32 bytes
FEX-Emu · Mar 21, 2024 · 167896d · 167896d
2 parents 7dcacfe + 12fb26f
commit 167896d
Show file tree

Hide file tree

Showing 3 changed files with 159 additions and 160 deletions.
diff --git a/FEXCore/Source/Interface/Core/JIT/Arm64/MemoryOps.cpp b/FEXCore/Source/Interface/Core/JIT/Arm64/MemoryOps.cpp
@@ -1814,10 +1814,6 @@ DEF_OP(MemSet) {
       ARMEmitter::ForwardLabel AgainInternal128Exit{};
       ARMEmitter::BackwardLabel AgainInternal128{};
 
-      // Fallback to byte by byte loop if not 4 byte aligned
-      and_(ARMEmitter::Size::i64Bit, TMP4, TMP2, 0x3);
-      cbnz(ARMEmitter::Size::i64Bit, TMP4, &AgainInternal);
-
       if (Direction == -1) {
         sub(ARMEmitter::Size::i64Bit, TMP2, TMP2, 32 - Size);
       }
@@ -2127,15 +2123,18 @@ DEF_OP(MemCpy) {
     cbz(ARMEmitter::Size::i64Bit, TMP1, &DoneInternal);
 
     if (!Op->IsAtomic) {
+      ARMEmitter::ForwardLabel AbsPos{};
       ARMEmitter::ForwardLabel AgainInternal256Exit{};
       ARMEmitter::ForwardLabel AgainInternal128Exit{};
       ARMEmitter::BackwardLabel AgainInternal128{};
       ARMEmitter::BackwardLabel AgainInternal256{};
 
-      // Fallback to byte by byte loop if either of start/end are not 4 byte aligned
-      orr(ARMEmitter::Size::i64Bit, TMP4, TMP2, TMP3);
-      and_(ARMEmitter::Size::i64Bit, TMP4, TMP4, 0x3);
-      cbnz(ARMEmitter::Size::i64Bit, TMP4, &AgainInternal);
+      sub(ARMEmitter::Size::i64Bit, TMP4, TMP2, TMP3);
+      tbz(TMP4, 63, &AbsPos);
+      neg(ARMEmitter::Size::i64Bit, TMP4, TMP4);
+      Bind(&AbsPos);
+      sub(ARMEmitter::Size::i64Bit, TMP4, TMP4, 32);
+      tbnz(TMP4, 63, &AgainInternal);
 
       if (Direction == -1) {
         sub(ARMEmitter::Size::i64Bit, TMP2, TMP2, 32 - Size);