generalize the previous code to use the full generality of LEA
for i32/i64 expressions (we could also do i16 on cpus where
i16 lea is fast, but I didn't add this). On the example, we now
generate:
_test:
movl 4(%esp), %eax
cmpl $42, (%eax)
setl %al
movzbl %al, %eax
leal 4(%eax,%eax,8), %eax
ret
instead of:
_test:
movl 4(%esp), %eax
cmpl $41, (%eax)
movl $4, %ecx
movl $13, %eax
cmovg %ecx, %eax
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@66869 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/test/CodeGen/X86/select-no-cmov.ll b/test/CodeGen/X86/select-no-cmov.ll
index 87382fe..71636f9 100644
--- a/test/CodeGen/X86/select-no-cmov.ll
+++ b/test/CodeGen/X86/select-no-cmov.ll
@@ -12,3 +12,15 @@
%iftmp.0.0 = select i1 %1, i32 -1, i32 -2 ; <i32> [#uses=1]
ret i32 %iftmp.0.0
}
+
+; setl %al
+; movzbl %al, %eax
+; leal 4(%eax,%eax,8), %eax
+define i32 @test2(i32* nocapture %P) nounwind readonly {
+entry:
+ %0 = load i32* %P, align 4 ; <i32> [#uses=1]
+ %1 = icmp sgt i32 %0, 41 ; <i1> [#uses=1]
+ %iftmp.0.0 = select i1 %1, i32 4, i32 13 ; <i32> [#uses=1]
+ ret i32 %iftmp.0.0
+}
+