diff options
| author | Benjamin Kramer <benny.kra@googlemail.com> | 2011-01-30 16:38:43 +0000 |
|---|---|---|
| committer | Benjamin Kramer <benny.kra@googlemail.com> | 2011-01-30 16:38:43 +0000 |
| commit | 9b108a338d544a6baf2ff087055326e301e6815d (patch) | |
| tree | 345e4c3631032d90ad172e06bc26fef3c0b3ebf3 /test | |
| parent | bb25e2c91b79fc31103510860e1817863a674bc5 (diff) | |
| download | external_llvm-9b108a338d544a6baf2ff087055326e301e6815d.zip external_llvm-9b108a338d544a6baf2ff087055326e301e6815d.tar.gz external_llvm-9b108a338d544a6baf2ff087055326e301e6815d.tar.bz2 | |
Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off.
This happens all the time when a smul is promoted to a larger type.
On x86-64 we now compile "int test(int x) { return x/10; }" into
movslq %edi, %rax
imulq $1717986919, %rax, %rax
movq %rax, %rcx
shrq $63, %rcx
sarq $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax"
addl %ecx, %eax
This fires 96 times in gcc.c on x86-64.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124559 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test')
| -rw-r--r-- | test/CodeGen/X86/divide-by-constant.ll | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/test/CodeGen/X86/divide-by-constant.ll b/test/CodeGen/X86/divide-by-constant.ll index 545662f..7ceb972 100644 --- a/test/CodeGen/X86/divide-by-constant.ll +++ b/test/CodeGen/X86/divide-by-constant.ll @@ -51,3 +51,12 @@ define i32 @test5(i32 %A) nounwind { ; CHECK: mull 4(%esp) } +define signext i16 @test6(i16 signext %x) nounwind { +entry: + %div = sdiv i16 %x, 10 + ret i16 %div +; CHECK: test6: +; CHECK: imull $26215, %eax, %eax +; CHECK: shrl $31, %ecx +; CHECK: sarl $18, %eax +} |