llvm-6502/test/CodeGen/X86/memset-2.ll
Benjamin Kramer 8c06aa1c59 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


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@122707 91177308-0d34-0410-b5e6-96231b3b80d8
2011-01-02 19:44:58 +00:00

31 lines
735 B
LLVM

; RUN: llc -mtriple=i386-apple-darwin < %s | FileCheck %s
declare void @llvm.memset.i32(i8*, i8, i32, i32) nounwind
define fastcc void @t1() nounwind {
entry:
; CHECK: t1:
; CHECK: calll _memset
call void @llvm.memset.i32( i8* null, i8 0, i32 188, i32 1 ) nounwind
unreachable
}
define fastcc void @t2(i8 signext %c) nounwind {
entry:
; CHECK: t2:
; CHECK: calll _memset
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
}