Many of the SSE patterns should not be selected when AVX is available. This led to the following code in X86Subtarget.cpp

  if (HasAVX)
    X86SSELevel = NoMMXSSE;

This is so patterns that are predicated on hasSSE3, etc. would not be selected when avx is available. Instead, the AVX variant is selected.
However, this breaks instructions which do not have AVX variants.

The right way to fix this is for the SSE but not-AVX patterns to predicate on something like hasSSE3() && !hasAVX().
Then we can take out the hack in X86Subtarget.cpp. Patterns which do not have AVX variants do not need to change.

However, we need to audit all the patterns before we make the change. This patch is workaround that fixes one specific case,
the prefetch instructions. rdar://10538297

llvm-svn: 146163

4 files changed, 11 insertions, 4 deletions

diff --git a/llvm/lib/Target/X86/X86InstrFormats.td b/llvm/lib/Target/X86/X86InstrFormats.td
index 08c56c2e692..b568389f9b8 100644
--- a/llvm/lib/Target/X86/X86InstrFormats.td
+++ b/llvm/lib/Target/X86/X86InstrFormats.td
@@ -334,6 +334,10 @@ class VPSI<bits<8> o, Format F, dag outs, dag ins, string asm,
            list<dag> pattern>
       : I<o, F, outs, ins, !strconcat("v", asm), pattern, SSEPackedSingle>, TB,
         Requires<[HasAVX]>;
+class VoPSI<bits<8> o, Format F, dag outs, dag ins, string asm,
+            list<dag> pattern>
+      : I<o, F, outs, ins, asm, pattern, SSEPackedSingle>, TB,
+        Requires<[HasSSE1orAVX]>;
 
 // SSE2 Instruction Templates:
 // 
diff --git a/llvm/lib/Target/X86/X86InstrInfo.td b/llvm/lib/Target/X86/X86InstrInfo.td
index 5dbdf342e74..d293a140b92 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.td
+++ b/llvm/lib/Target/X86/X86InstrInfo.td
@@ -476,6 +476,8 @@ def HasAVX2      : Predicate<"Subtarget->hasAVX2()">;
 def HasXMM       : Predicate<"Subtarget->hasXMM()">;
 def HasXMMInt    : Predicate<"Subtarget->hasXMMInt()">;
 
+def HasSSE1orAVX : Predicate<"Subtarget->hasSSE1orAVX()">;
+
 def HasPOPCNT    : Predicate<"Subtarget->hasPOPCNT()">;
 def HasAES       : Predicate<"Subtarget->hasAES()">;
 def HasCLMUL     : Predicate<"Subtarget->hasCLMUL()">;
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 9b1caad6043..836c01667f3 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -3183,13 +3183,13 @@ def MOVNTI_64mr : RI<0xC3, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
 //===----------------------------------------------------------------------===//
 
 // Prefetch intrinsic.
-def PREFETCHT0   : PSI<0x18, MRM1m, (outs), (ins i8mem:$src),
+def PREFETCHT0   : VoPSI<0x18, MRM1m, (outs), (ins i8mem:$src),
     "prefetcht0\t$src", [(prefetch addr:$src, imm, (i32 3), (i32 1))]>;
-def PREFETCHT1   : PSI<0x18, MRM2m, (outs), (ins i8mem:$src),
+def PREFETCHT1   : VoPSI<0x18, MRM2m, (outs), (ins i8mem:$src),
     "prefetcht1\t$src", [(prefetch addr:$src, imm, (i32 2), (i32 1))]>;
-def PREFETCHT2   : PSI<0x18, MRM3m, (outs), (ins i8mem:$src),
+def PREFETCHT2   : VoPSI<0x18, MRM3m, (outs), (ins i8mem:$src),
     "prefetcht2\t$src", [(prefetch addr:$src, imm, (i32 1), (i32 1))]>;
-def PREFETCHNTA  : PSI<0x18, MRM0m, (outs), (ins i8mem:$src),
+def PREFETCHNTA  : VoPSI<0x18, MRM0m, (outs), (ins i8mem:$src),
     "prefetchnta\t$src", [(prefetch addr:$src, imm, (i32 0), (i32 1))]>;
 
 // Flush cache
diff --git a/llvm/lib/Target/X86/X86Subtarget.h b/llvm/lib/Target/X86/X86Subtarget.h
index ccb9be0c97a..b8a2a1fdad6 100644
--- a/llvm/lib/Target/X86/X86Subtarget.h
+++ b/llvm/lib/Target/X86/X86Subtarget.h
@@ -193,6 +193,7 @@ public:
   bool hasAVX2() const { return HasAVX2; }
   bool hasXMM() const { return hasSSE1() || hasAVX(); }
   bool hasXMMInt() const { return hasSSE2() || hasAVX(); }
+  bool hasSSE1orAVX() const { return hasSSE1() || hasAVX(); }
   bool hasSSE3orAVX() const { return hasSSE3() || hasAVX(); }
   bool hasSSSE3orAVX() const { return hasSSSE3() || hasAVX(); }
   bool hasSSE41orAVX() const { return hasSSE41() || hasAVX(); }