| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py |
| ; 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 { |
| ; CHECK-LABEL: test1: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: jne LBB0_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI0_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB0_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI0_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 { |
| ; CHECK-LABEL: test3: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: jne LBB1_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI1_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB1_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI1_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 { |
| ; CHECK-LABEL: test4: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: jae LBB2_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI2_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB2_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI2_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 { |
| ; CHECK-LABEL: test6: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: jae LBB3_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI3_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB3_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI3_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 { |
| ; CHECK-LABEL: test7: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: jne LBB4_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI4_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB4_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI4_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 { |
| ; CHECK-LABEL: test8: |
| ; CHECK: ## %bb.0: ## %entry |
| ; CHECK-NEXT: vptest %ymm0, %ymm0 |
| ; CHECK-NEXT: je LBB5_2 |
| ; CHECK-NEXT: ## %bb.1: ## %bb1 |
| ; CHECK-NEXT: vaddps LCPI5_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| ; CHECK-NEXT: LBB5_2: ## %bb2 |
| ; CHECK-NEXT: vdivps LCPI5_0, %xmm1, %xmm0 |
| ; CHECK-NEXT: vzeroupper |
| ; CHECK-NEXT: retl |
| entry: |
| |
| %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 |
| } |
| |
| |