[llvm-commits] [llvm] r43230 - in /llvm/trunk: lib/Target/X86/X86ISelDAGToDAG.cpp test/CodeGen/X86/fold-mul-lohi.ll

[Dan Gohman]

Author: djg
Date: Mon Oct 22 15:22:24 2007
New Revision: 43230

URL: http://llvm.org/viewvc/llvm-project?rev=43230&view=rev
Log:
Fix the folding of multiplication into addresses on x86, which was broken
by the recent {U,S}MUL_LOHI changes.

Added:
    llvm/trunk/test/CodeGen/X86/fold-mul-lohi.ll
Modified:
    llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp

Modified: llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp?rev=43230&r1=43229&r2=43230&view=diff

==============================================================================
--- llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86ISelDAGToDAG.cpp Mon Oct 22 15:22:24 2007
@@ -681,6 +681,11 @@
       }
     break;
 
+  case ISD::SMUL_LOHI:
+  case ISD::UMUL_LOHI:
+    // A mul_lohi where we need the low part can be folded as a plain multiply.
+    if (N.ResNo != 0) break;
+    // FALL THROUGH
   case ISD::MUL:
     // X*[3,5,9] -> X+X*[2,4,8]
     if (!Available &&

Added: llvm/trunk/test/CodeGen/X86/fold-mul-lohi.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/fold-mul-lohi.ll?rev=43230&view=auto

==============================================================================
--- llvm/trunk/test/CodeGen/X86/fold-mul-lohi.ll (added)
+++ llvm/trunk/test/CodeGen/X86/fold-mul-lohi.ll Mon Oct 22 15:22:24 2007
@@ -0,0 +1,30 @@
+; RUN: llvm-as < %s | llc -march=x86 | not grep lea
+; RUN: llvm-as < %s | llc -march=x86-64 | not grep lea
+
+ at B = external global [1000 x i8], align 32
+ at A = external global [1000 x i8], align 32
+ at P = external global [1000 x i8], align 32
+
+define void @foo(i32 %m) {
+entry:
+	%tmp1 = icmp sgt i32 %m, 0
+	br i1 %tmp1, label %bb, label %return
+
+bb:
+	%i.019.0 = phi i32 [ %indvar.next, %bb ], [ 0, %entry ]
+	%tmp2 = getelementptr [1000 x i8]* @B, i32 0, i32 %i.019.0
+	%tmp3 = load i8* %tmp2, align 4
+	%tmp4 = mul i8 %tmp3, 2
+	%tmp5 = getelementptr [1000 x i8]* @A, i32 0, i32 %i.019.0
+	store i8 %tmp4, i8* %tmp5, align 4
+	%tmp8 = mul i32 %i.019.0, 9
+	%tmp10 = getelementptr [1000 x i8]* @P, i32 0, i32 %tmp8
+	store i8 17, i8* %tmp10, align 4
+	%indvar.next = add i32 %i.019.0, 1
+	%exitcond = icmp eq i32 %indvar.next, %m
+	br i1 %exitcond, label %return, label %bb
+
+return:
+	ret void
+}
+