forked from OSchip/llvm-project
200 lines
5.9 KiB
LLVM
200 lines
5.9 KiB
LLVM
; 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
|
|
}
|
|
|
|
|