[x86, SSE] update packed FP compare tests for direct translation from builtin to IR

The clang side of this was r272840:
http://reviews.llvm.org/rL272840

A follow-up step would be to auto-upgrade and remove these LLVM intrinsics completely.

Differential Revision: http://reviews.llvm.org/D21269

llvm-svn: 272841

1 files changed, 36 insertions, 13 deletions

diff --git a/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll b/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
index 8d7f6c33e6d..fe63b82f814 100644
--- a/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
+++ b/llvm/test/CodeGen/X86/sse-intrinsics-fast-isel.ll
@@ -196,10 +196,11 @@ define <4 x float> @test_mm_cmpeq_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpeqps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 0)
+  %cmp = fcmp oeq <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse.cmp.ps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 define <4 x float> @test_mm_cmpeq_ss(<4 x float> %a0, <4 x float> %a1) nounwind {
 ; X32-LABEL: test_mm_cmpeq_ss:
@@ -228,7 +229,9 @@ define <4 x float> @test_mm_cmpge_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64-NEXT:    cmpleps %xmm0, %xmm1
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a1, <4 x float> %a0, i8 2)
+  %cmp = fcmp ole <4 x float> %a1, %a0
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -261,7 +264,9 @@ define <4 x float> @test_mm_cmpgt_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64-NEXT:    cmpltps %xmm0, %xmm1
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a1, <4 x float> %a0, i8 1)
+  %cmp = fcmp olt <4 x float> %a1, %a0
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -292,7 +297,9 @@ define <4 x float> @test_mm_cmple_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpleps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 2)
+  %cmp = fcmp ole <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -320,7 +327,9 @@ define <4 x float> @test_mm_cmplt_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpltps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 1)
+  %cmp = fcmp olt <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -348,7 +357,9 @@ define <4 x float> @test_mm_cmpneq_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpneqps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 4)
+  %cmp = fcmp une <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -378,7 +389,9 @@ define <4 x float> @test_mm_cmpnge_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64-NEXT:    cmpnleps %xmm0, %xmm1
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a1, <4 x float> %a0, i8 6)
+  %cmp = fcmp ugt <4 x float> %a1, %a0
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -411,7 +424,9 @@ define <4 x float> @test_mm_cmpngt_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64-NEXT:    cmpnltps %xmm0, %xmm1
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a1, <4 x float> %a0, i8 5)
+  %cmp = fcmp uge <4 x float> %a1, %a0
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -442,7 +457,9 @@ define <4 x float> @test_mm_cmpnle_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpnleps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 6)
+  %cmp = fcmp ugt <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -470,7 +487,9 @@ define <4 x float> @test_mm_cmpnlt_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpnltps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 5)
+  %cmp = fcmp uge <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -498,7 +517,9 @@ define <4 x float> @test_mm_cmpord_ps(<4 x float> %a0, <4 x float> %a1) nounwind
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpordps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 7)
+  %cmp = fcmp ord <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }
 
@@ -526,7 +547,9 @@ define <4 x float> @test_mm_cmpunord_ps(<4 x float> %a0, <4 x float> %a1) nounwi
 ; X64:       # BB#0:
 ; X64-NEXT:    cmpunordps %xmm1, %xmm0
 ; X64-NEXT:    retq
-  %res = call <4 x float> @llvm.x86.sse.cmp.ps(<4 x float> %a0, <4 x float> %a1, i8 3)
+  %cmp = fcmp uno <4 x float> %a0, %a1
+  %sext = sext <4 x i1> %cmp to <4 x i32>
+  %res = bitcast <4 x i32> %sext to <4 x float>
   ret <4 x float> %res
 }