diff options
author | Dan Gohman <gohman@apple.com> | 2007-10-22 20:22:24 +0000 |
---|---|---|
committer | Dan Gohman <gohman@apple.com> | 2007-10-22 20:22:24 +0000 |
commit | 8368805e255d53a68f89e341b69ed0f7022509c4 (patch) | |
tree | 3001a6ca933b91076142672283624f87cfdda81a | |
parent | 3311876c3c3147688b08f64c441e5bfaaa3412b3 (diff) | |
download | llvm-8368805e255d53a68f89e341b69ed0f7022509c4.tar.gz llvm-8368805e255d53a68f89e341b69ed0f7022509c4.tar.bz2 llvm-8368805e255d53a68f89e341b69ed0f7022509c4.tar.xz |
Fix the folding of multiplication into addresses on x86, which was broken
by the recent {U,S}MUL_LOHI changes.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@43230 91177308-0d34-0410-b5e6-96231b3b80d8
-rw-r--r-- | lib/Target/X86/X86ISelDAGToDAG.cpp | 5 | ||||
-rw-r--r-- | test/CodeGen/X86/fold-mul-lohi.ll | 30 |
2 files changed, 35 insertions, 0 deletions
diff --git a/lib/Target/X86/X86ISelDAGToDAG.cpp b/lib/Target/X86/X86ISelDAGToDAG.cpp index 853ac114df..9b7808eaa7 100644 --- a/lib/Target/X86/X86ISelDAGToDAG.cpp +++ b/lib/Target/X86/X86ISelDAGToDAG.cpp @@ -681,6 +681,11 @@ bool X86DAGToDAGISel::MatchAddress(SDOperand N, X86ISelAddressMode &AM, } 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 && diff --git a/test/CodeGen/X86/fold-mul-lohi.ll b/test/CodeGen/X86/fold-mul-lohi.ll new file mode 100644 index 0000000000..abd8ddd92c --- /dev/null +++ b/test/CodeGen/X86/fold-mul-lohi.ll @@ -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 + +@B = external global [1000 x i8], align 32 +@A = external global [1000 x i8], align 32 +@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 +} + |