[AVX512] Bring back vector-shuffle lowering support through broadcasts

[oota-llvm.git] / test / CodeGen / X86 / brcond.ll

diff --git a/test/CodeGen/X86/brcond.ll b/test/CodeGen/X86/brcond.ll
index fa74aa3c9a632056c3c6b8d71f0e6cbf0f27a3b6..3ebe1a1d235751385d2976c3ec39f1aa35e9c22b 100644 (file)
--- a/test/CodeGen/X86/brcond.ll
+++ b/test/CodeGen/X86/brcond.ll
@@ -1,9 +1,10 @@
-; RUN: llc < %s -mtriple=i386-apple-darwin10 | FileCheck %s
+; RUN: llc < %s -mtriple=i386-apple-darwin10 -mcpu=penryn | FileCheck %s
+
 ; rdar://7475489
 
 define i32 @test1(i32 %a, i32 %b) nounwind ssp {
 entry:
-; CHECK: test1:
+; CHECK-LABEL: test1:
 ; CHECK: xorb
 ; CHECK-NOT: andb
 ; CHECK-NOT: shrb
@@ -43,10 +44,10 @@ bb1:                                              ; preds = %entry
 
 return:                                           ; preds = %entry
   ret i32 192
-; CHECK: test2:
+; CHECK-LABEL: test2:
 ; CHECK:       movl    4(%esp), %eax
 ; CHECK-NEXT:  orl     8(%esp), %eax
-; CHECK-NEXT:  jne     LBB2_2
+; CHECK-NEXT:  jne     LBB1_2
 }
 
 ; PR3351 - (P != 0) | (Q != 0) -> (P|Q) != 0
@@ -62,10 +63,10 @@ bb1:                                              ; preds = %entry
 
 return:                                           ; preds = %entry
   ret i32 192
-; CHECK: test3:
+; CHECK-LABEL: test3:
 ; CHECK:       movl    4(%esp), %eax
 ; CHECK-NEXT:  orl     8(%esp), %eax
-; CHECK-NEXT:  je      LBB3_2
+; CHECK-NEXT:  je      LBB2_2
 }
 
 ; <rdar://problem/7598384>:
@@ -95,7 +96,7 @@ entry:
 ; CHECK:      jne
 ; CHECK-NEXT: jnp
 ; CHECK-NOT:  jmp
-; CHECK-NEXT: LBB
+; CHECK:      LBB
 
 bb1:                                              ; preds = %entry
   %4 = fadd double %2, -1.000000e+00              ; <double> [#uses=1]
@@ -106,3 +107,151 @@ bb2:                                              ; preds = %entry, %bb1
   %.0 = fptrunc double %.0.in to float            ; <float> [#uses=1]
   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-LABEL: 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-LABEL: 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-LABEL: 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-LABEL: 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-LABEL: 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-LABEL: 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
+}
+