diff options
author | Michael Liao <michael.liao@intel.com> | 2013-04-11 04:43:09 +0000 |
---|---|---|
committer | Michael Liao <michael.liao@intel.com> | 2013-04-11 04:43:09 +0000 |
commit | 959ddbb5e0e088f4d5c3f8c015de3caf0baa6e6c (patch) | |
tree | 37bea38003bfa703a6fa095535f65763b618565e /test/CodeGen | |
parent | 4eb5f18956a8e3a0652039f657272729e2381aed (diff) | |
download | llvm-959ddbb5e0e088f4d5c3f8c015de3caf0baa6e6c.tar.gz llvm-959ddbb5e0e088f4d5c3f8c015de3caf0baa6e6c.tar.bz2 llvm-959ddbb5e0e088f4d5c3f8c015de3caf0baa6e6c.tar.xz |
Enhance bool simplifcation in X86 to handle more cases
This patch is revised based on patch from Victor Umansky
<victor.umansky@intel.com>. More cases are handled in X86's bool
simplification, i.e.
- SETCC_CARRY
- value is truncated to i1 with AND
As a by-product, PR5443 is also fixed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179265 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/CodeGen')
-rw-r--r-- | test/CodeGen/X86/add.ll | 4 | ||||
-rw-r--r-- | test/CodeGen/X86/avx-brcond.ll | 150 | ||||
-rw-r--r-- | test/CodeGen/X86/brcond.ll | 147 |
3 files changed, 299 insertions, 2 deletions
diff --git a/test/CodeGen/X86/add.ll b/test/CodeGen/X86/add.ll index 03d2e472cb..5fe08ed305 100644 --- a/test/CodeGen/X86/add.ll +++ b/test/CodeGen/X86/add.ll @@ -119,8 +119,8 @@ entry: ; X64: test8: ; X64: addq -; X64-NEXT: sbbq -; X64-NEXT: testb +; X64-NEXT: setb +; X64: ret define i32 @test9(i32 %x, i32 %y) nounwind readnone { %cmp = icmp eq i32 %x, 10 diff --git a/test/CodeGen/X86/avx-brcond.ll b/test/CodeGen/X86/avx-brcond.ll new file mode 100644 index 0000000000..d52ae52e0b --- /dev/null +++ b/test/CodeGen/X86/avx-brcond.ll @@ -0,0 +1,150 @@ +; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=corei7-avx -mattr=+avx | FileCheck %s + +declare i32 @llvm.x86.avx.ptestz.256(<4 x i64> %p1, <4 x i64> %p2) nounwind +declare i32 @llvm.x86.avx.ptestc.256(<4 x i64> %p1, <4 x i64> %p2) nounwind + +define <4 x float> @test1(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test1: +; CHECK: vptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = icmp ne i32 %res, 0 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test3(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test3: +; CHECK: vptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = trunc i32 %res to i1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test4(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test4: +; CHECK: vptest +; CHECK-NEXT: jae +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = icmp ne i32 %res, 0 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test6(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test6: +; CHECK: vptest +; CHECK-NEXT: jae +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestc.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = trunc i32 %res to i1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test7(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test7: +; CHECK: vptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = icmp eq i32 %res, 1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test8(<4 x i64> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test8: +; CHECK: vptest +; CHECK-NEXT: je +; CHECK: ret + + %res = call i32 @llvm.x86.avx.ptestz.256(<4 x i64> %a, <4 x i64> %a) nounwind + %one = icmp ne i32 %res, 1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + + diff --git a/test/CodeGen/X86/brcond.ll b/test/CodeGen/X86/brcond.ll index 44670c802b..bc4032b13c 100644 --- a/test/CodeGen/X86/brcond.ll +++ b/test/CodeGen/X86/brcond.ll @@ -108,3 +108,150 @@ bb2: ; preds = %entry, %bb1 ret float %.0 } +declare i32 @llvm.x86.sse41.ptestz(<4 x float> %p1, <4 x float> %p2) nounwind +declare i32 @llvm.x86.sse41.ptestc(<4 x float> %p1, <4 x float> %p2) nounwind + +define <4 x float> @test5(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test5: +; CHECK: ptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind + %one = icmp ne i32 %res, 0 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test7(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test7: +; CHECK: ptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind + %one = trunc i32 %res to i1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test8(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test8: +; CHECK: ptest +; CHECK-NEXT: jae +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind + %one = icmp ne i32 %res, 0 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test10(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test10: +; CHECK: ptest +; CHECK-NEXT: jae +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestc(<4 x float> %a, <4 x float> %a) nounwind + %one = trunc i32 %res to i1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test11(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test11: +; CHECK: ptest +; CHECK-NEXT: jne +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind + %one = icmp eq i32 %res, 1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + +define <4 x float> @test12(<4 x float> %a, <4 x float> %b) nounwind { +entry: +; CHECK: test12: +; CHECK: ptest +; CHECK-NEXT: je +; CHECK: ret + + %res = call i32 @llvm.x86.sse41.ptestz(<4 x float> %a, <4 x float> %a) nounwind + %one = icmp ne i32 %res, 1 + br i1 %one, label %bb1, label %bb2 + +bb1: + %c = fadd <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +bb2: + %d = fdiv <4 x float> %b, < float 1.000000e+002, float 2.000000e+002, float 3.000000e+002, float 4.000000e+002 > + br label %return + +return: + %e = phi <4 x float> [%c, %bb1], [%d, %bb2] + ret <4 x float> %e +} + |