On x86, it's safe to treat i32 load anyext as a normal i32 load. Ditto for i8 anyext load to i16.

llvm-svn: 51019

2 files changed, 28 insertions, 27 deletions

diff --git a/llvm/lib/Target/X86/README-SSE.txt b/llvm/lib/Target/X86/README-SSE.txt
index 34b949a6018..c78e13b8a8b 100644
--- a/llvm/lib/Target/X86/README-SSE.txt
+++ b/llvm/lib/Target/X86/README-SSE.txt
@@ -757,31 +757,6 @@ or iseling it.
 
 //===---------------------------------------------------------------------===//
 
-Take the following code:
-
-#include <xmmintrin.h>
-__m128i doload64(short x) {return _mm_set_epi16(x,x,x,x,x,x,x,x);}
-
-LLVM currently generates the following on x86:
-doload64:
-        movzwl  4(%esp), %eax
-        movd    %eax, %xmm0
-        punpcklwd       %xmm0, %xmm0
-        pshufd  $0, %xmm0, %xmm0
-        ret
-
-gcc's generated code:
-doload64:
-        movd    4(%esp), %xmm0
-        punpcklwd       %xmm0, %xmm0
-        pshufd  $0, %xmm0, %xmm0
-        ret
-
-LLVM should be able to generate the same thing as gcc.  This looks like it is
-just a matter of matching (scalar_to_vector (load x)) to movd.
-
-//===---------------------------------------------------------------------===//
-
 LLVM currently generates stack realignment code, when it is not necessary
 needed. The problem is that we need to know about stack alignment too early,
 before RA runs.
diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td
index 6b0a19bb4d7..afe420625c9 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.td
+++ b/llvm/lib/Target/X86/X86InstrInfo.td
@@ -229,9 +229,35 @@ def i32immSExt8  : PatLeaf<(i32 imm), [{
 }]>;
 
 // Helper fragments for loads.
+// It's always safe to treat a anyext i16 load as a i32 load. Ditto for
+// i8 to i16.
+def loadi16 : PatFrag<(ops node:$ptr), (i16 (ld node:$ptr)), [{
+  if (LoadSDNode *LD = dyn_cast<LoadSDNode>(N)) {
+    if (LD->getAddressingMode() != ISD::UNINDEXED)
+      return false;
+    ISD::LoadExtType ExtType = LD->getExtensionType();
+    if (ExtType == ISD::NON_EXTLOAD)
+      return true;
+    if (ExtType == ISD::EXTLOAD)
+      return LD->getAlignment() >= 16;
+  }
+  return false;
+}]>;
+
+def loadi32 : PatFrag<(ops node:$ptr), (i32 (ld node:$ptr)), [{
+  if (LoadSDNode *LD = dyn_cast<LoadSDNode>(N)) {
+    if (LD->getAddressingMode() != ISD::UNINDEXED)
+      return false;
+    ISD::LoadExtType ExtType = LD->getExtensionType();
+    if (ExtType == ISD::NON_EXTLOAD)
+      return true;
+    if (ExtType == ISD::EXTLOAD)
+      return LD->getAlignment() >= 16;
+  }
+  return false;
+}]>;
+
 def loadi8  : PatFrag<(ops node:$ptr), (i8  (load node:$ptr))>;
-def loadi16 : PatFrag<(ops node:$ptr), (i16 (load node:$ptr))>;
-def loadi32 : PatFrag<(ops node:$ptr), (i32 (load node:$ptr))>;
 def loadi64 : PatFrag<(ops node:$ptr), (i64 (load node:$ptr))>;
 
 def loadf32 : PatFrag<(ops node:$ptr), (f32 (load node:$ptr))>;