Lower the i8 extension in memset to a multiply instead of a potentially long series of shifts and ors.

We could implement a DAGCombine to turn x * 0x0101 back into logic operations
on targets that doesn't support the multiply or it is slow (p4) if someone cares
enough.

Example code:
  void test(char *s, int a) {
      __builtin_memset(s, a, 4);
  }
before:
  _test:                                  ## @test
    movzbl  8(%esp), %eax
    movl  %eax, %ecx
    shll  $8, %ecx
    orl %eax, %ecx
    movl  %ecx, %eax
    shll  $16, %eax
    orl %ecx, %eax
    movl  4(%esp), %ecx
    movl  %eax, 4(%ecx)
    movl  %eax, (%ecx)
    ret
after:
  _test:                                  ## @test
    movzbl  8(%esp), %eax
    imull $16843009, %eax, %eax   ## imm = 0x1010101
    movl  4(%esp), %ecx
    movl  %eax, 4(%ecx)
    movl  %eax, (%ecx)
    ret

llvm-svn: 122707

1 files changed, 11 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/memset-2.ll b/llvm/test/CodeGen/X86/memset-2.ll
index 692965f6f7e..11f619cd6da 100644
--- a/llvm/test/CodeGen/X86/memset-2.ll
+++ b/llvm/test/CodeGen/X86/memset-2.ll
@@ -17,3 +17,14 @@ entry:
   call void @llvm.memset.i32( i8* undef, i8 %c, i32 76, i32 1 ) nounwind
   unreachable
 }
+
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
+
+define void @t3(i8* nocapture %s, i8 %a) nounwind {
+entry:
+  tail call void @llvm.memset.p0i8.i32(i8* %s, i8 %a, i32 8, i32 1, i1 false)
+  ret void
+; CHECK: t3:
+; CHECK: imull $16843009
+}
+