[x86] Merge the remaining test cases into vector-blend.ll and remove all

the ISA-specific test files.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218818 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 117 insertions, 218 deletions

diff --git a/test/CodeGen/X86/avx2-blend.ll b/test/CodeGen/X86/avx2-blend.ll
deleted file mode 100644
index b02442b6fad..00000000000
--- a/test/CodeGen/X86/avx2-blend.ll
+++ /dev/null
@@ -1,11 +0,0 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=core-avx2 | FileCheck %s
-
-define <32 x i8> @constant_pblendvb_avx2(<32 x i8> %xyzw, <32 x i8> %abcd) {
-; CHECK-LABEL: constant_pblendvb_avx2:
-; CHECK: vmovdqa
-; CHECK: vpblendvb
-  %1 = select <32 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <32 x i8> %xyzw, <32 x i8> %abcd
-  ret <32 x i8> %1
-}
-
-declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>)
diff --git a/test/CodeGen/X86/sse2-blend.ll b/test/CodeGen/X86/sse2-blend.ll
deleted file mode 100644
index c63ff72b480..00000000000
--- a/test/CodeGen/X86/sse2-blend.ll
+++ /dev/null
@@ -1,57 +0,0 @@
-; RUN: llc < %s -march=x86 -mcpu=yonah -mattr=+sse2,-sse4.1 | FileCheck %s
-
-; CHECK-LABEL: vsel_float
-; CHECK-NOT: xorps
-; CHECK: movss
-; CHECK-NOT: orps
-; CHECK: ret
-define void@vsel_float(<4 x float>* %v1, <4 x float>* %v2) {
-  %A = load <4 x float>* %v1
-  %B = load <4 x float>* %v2
-  %vsel = select <4 x i1> <i1 false, i1 true, i1 true, i1 true>, <4 x float> %A, <4 x float> %B
-  store <4 x float > %vsel, <4 x float>* %v1
-  ret void
-}
-
-; CHECK-LABEL: vsel_i32
-; CHECK-NOT: xorps
-; CHECK: movss
-; CHECK-NOT: orps
-; CHECK: ret
-define void@vsel_i32(<4 x i32>* %v1, <4 x i32>* %v2) {
-  %A = load <4 x i32>* %v1
-  %B = load <4 x i32>* %v2
-  %vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i32> %A, <4 x i32> %B
-  store <4 x i32 > %vsel, <4 x i32>* %v1
-  ret void
-}
-
-; Without forcing instructions, fall back to the preferred PS domain.
-; CHECK-LABEL: vsel_i64
-; CHECK: andnps
-; CHECK: orps
-; CHECK: ret
-
-define void@vsel_i64(<2 x i64>* %v1, <2 x i64>* %v2) {
-  %A = load <2 x i64>* %v1
-  %B = load <2 x i64>* %v2
-  %vsel = select <2 x i1> <i1 true, i1 false>, <2 x i64> %A, <2 x i64> %B
-  store <2 x i64 > %vsel, <2 x i64>* %v1
-  ret void
-}
-
-; Without forcing instructions, fall back to the preferred PS domain.
-; CHECK-LABEL: vsel_double
-; CHECK: andnps
-; CHECK: orps
-; CHECK: ret
-
-define void@vsel_double(<2 x double>* %v1, <2 x double>* %v2) {
-  %A = load <2 x double>* %v1
-  %B = load <2 x double>* %v2
-  %vsel = select <2 x i1> <i1 true, i1 false>, <2 x double> %A, <2 x double> %B
-  store <2 x double > %vsel, <2 x double>* %v1
-  ret void
-}
-
-
diff --git a/test/CodeGen/X86/sse41-blend.ll b/test/CodeGen/X86/sse41-blend.ll
deleted file mode 100644
index 3992da0b512..00000000000
--- a/test/CodeGen/X86/sse41-blend.ll
+++ /dev/null
@@ -1,150 +0,0 @@
-; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse4.1 | FileCheck %s
-
-;CHECK-LABEL: vsel_float:
-;CHECK: blendps
-;CHECK: ret
-define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x float> %v1, <4 x float> %v2
-  ret <4 x float> %vsel
-}
-
-
-;CHECK-LABEL: vsel_4xi8:
-;CHECK: blendps
-;CHECK: ret
-define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 true, i1 false, i1 true>, <4 x i8> %v1, <4 x i8> %v2
-  ret <4 x i8> %vsel
-}
-
-;CHECK-LABEL: vsel_4xi16:
-;CHECK: blendps
-;CHECK: ret
-define <4 x i16> @vsel_4xi16(<4 x i16> %v1, <4 x i16> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x i16> %v1, <4 x i16> %v2
-  ret <4 x i16> %vsel
-}
-
-
-;CHECK-LABEL: vsel_i32:
-;CHECK: blendps
-;CHECK: ret
-define <4 x i32> @vsel_i32(<4 x i32> %v1, <4 x i32> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 true, i1 false, i1 true>, <4 x i32> %v1, <4 x i32> %v2
-  ret <4 x i32> %vsel
-}
-
-
-;CHECK-LABEL: vsel_double:
-;CHECK: movsd
-;CHECK: ret
-define <4 x double> @vsel_double(<4 x double> %v1, <4 x double> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> %v1, <4 x double> %v2
-  ret <4 x double> %vsel
-}
-
-
-;CHECK-LABEL: vsel_i64:
-;CHECK: movsd
-;CHECK: ret
-define <4 x i64> @vsel_i64(<4 x i64> %v1, <4 x i64> %v2) {
-  %vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> %v1, <4 x i64> %v2
-  ret <4 x i64> %vsel
-}
-
-
-;CHECK-LABEL: vsel_i8:
-;CHECK: pblendvb
-;CHECK: ret
-define <16 x i8> @vsel_i8(<16 x i8> %v1, <16 x i8> %v2) {
-  %vsel = select <16 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <16 x i8> %v1, <16 x i8> %v2
-  ret <16 x i8> %vsel
-}
-
-;; TEST blend + compares
-; CHECK: A
-define <2 x double> @A(<2 x double> %x, <2 x double> %y) {
-  ; CHECK: cmplepd
-  ; CHECK: blendvpd
-  %max_is_x = fcmp oge <2 x double> %x, %y
-  %max = select <2 x i1> %max_is_x, <2 x double> %x, <2 x double> %y
-  ret <2 x double> %max
-}
-
-; CHECK: B
-define <2 x double> @B(<2 x double> %x, <2 x double> %y) {
-  ; CHECK: cmpnlepd
-  ; CHECK: blendvpd
-  %min_is_x = fcmp ult <2 x double> %x, %y
-  %min = select <2 x i1> %min_is_x, <2 x double> %x, <2 x double> %y
-  ret <2 x double> %min
-}
-
-; CHECK: float_crash
-define void @float_crash() nounwind {
-entry:
-  %merge205vector_func.i = select <4 x i1> undef, <4 x double> undef, <4 x double> undef
-  %extract214vector_func.i = extractelement <4 x double> %merge205vector_func.i, i32 0
-  store double %extract214vector_func.i, double addrspace(1)* undef, align 8
-  ret void
-}
-
-; If we can figure out a blend has a constant mask, we should emit the
-; blend instruction with an immediate mask
-define <2 x double> @constant_blendvpd(<2 x double> %xy, <2 x double> %ab) {
-; In this case, we emit a simple movss
-; CHECK-LABEL: constant_blendvpd
-; CHECK: movsd
-; CHECK: ret
-  %1 = select <2 x i1> <i1 true, i1 false>, <2 x double> %xy, <2 x double> %ab
-  ret <2 x double> %1
-}
-
-define <4 x float> @constant_blendvps(<4 x float> %xyzw, <4 x float> %abcd) {
-; CHECK-LABEL: constant_blendvps
-; CHECK-NOT: mov
-; CHECK: blendps $7
-; CHECK: ret
-  %1 = select <4 x i1> <i1 false, i1 false, i1 false, i1 true>, <4 x float> %xyzw, <4 x float> %abcd
-  ret <4 x float> %1
-}
-
-define <16 x i8> @constant_pblendvb(<16 x i8> %xyzw, <16 x i8> %abcd) {
-; CHECK-LABEL: constant_pblendvb:
-; CHECK: movaps
-; CHECK: pblendvb
-; CHECK: ret
-  %1 = select <16 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <16 x i8> %xyzw, <16 x i8> %abcd
-  ret <16 x i8> %1
-}
-
-declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>)
-declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>)
-declare <2 x double> @llvm.x86.sse41.blendvpd(<2 x double>, <2 x double>, <2 x double>)
-
-;; 2 tests for shufflevectors that optimize to blend + immediate
-; CHECK-LABEL: @blend_shufflevector_4xfloat
-; CHECK: blendps $6, %xmm1, %xmm0
-; CHECK: ret
-define <4 x float> @blend_shufflevector_4xfloat(<4 x float> %a, <4 x float> %b) {
-  %1 = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 5, i32 6, i32 3>
-  ret <4 x float> %1
-}
-
-; CHECK-LABEL: @blend_shufflevector_8xi16
-; CHECK: pblendw $134, %xmm1, %xmm0
-; CHECK: ret
-define <8 x i16> @blend_shufflevector_8xi16(<8 x i16> %a, <8 x i16> %b) {
-  %1 = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 3, i32 4, i32 5, i32 6, i32 15>
-  ret <8 x i16> %1
-}
-
-; PR20648 - a blend of constants isn't really a blend; it's just a constant pool load.
-; CHECK-LABEL: @does_not_blend
-; CHECK: movaps
-; CHECK-NEXT: ret
-define <4 x i32> @does_not_blend() {
-  %select = select <4 x i1> <i1 1, i1 0, i1 0, i1 1>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
-  ret <4 x i32> %select
-}
-
diff --git a/test/CodeGen/X86/vector-blend.ll b/test/CodeGen/X86/vector-blend.ll
index 1465d8c61bd..7e5c10dd762 100644
--- a/test/CodeGen/X86/vector-blend.ll
+++ b/test/CodeGen/X86/vector-blend.ll
@@ -49,6 +49,72 @@ define <4 x float> @vsel_float2(<4 x float> %v1, <4 x float> %v2) {
   ret <4 x float> %vsel
 }
 
+define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) {
+; SSE2-LABEL: vsel_4xi8:
+; SSE2:       ## BB#0:
+; SSE2-NEXT:    andps {{.*}}, %xmm1
+; SSE2-NEXT:    andps {{.*}}, %xmm0
+; SSE2-NEXT:    orps %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: vsel_4xi8:
+; SSSE3:       ## BB#0:
+; SSSE3-NEXT:    andps {{.*}}, %xmm1
+; SSSE3-NEXT:    andps {{.*}}, %xmm0
+; SSSE3-NEXT:    orps %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: vsel_4xi8:
+; SSE41:       ## BB#0:
+; SSE41-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: vsel_4xi8:
+; AVX1:       ## BB#0:
+; AVX1-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: vsel_4xi8:
+; AVX2:       ## BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
+; AVX2-NEXT:    retq
+  %vsel = select <4 x i1> <i1 true, i1 true, i1 false, i1 true>, <4 x i8> %v1, <4 x i8> %v2
+  ret <4 x i8> %vsel
+}
+
+define <4 x i16> @vsel_4xi16(<4 x i16> %v1, <4 x i16> %v2) {
+; SSE2-LABEL: vsel_4xi16:
+; SSE2:       ## BB#0:
+; SSE2-NEXT:    andps {{.*}}, %xmm1
+; SSE2-NEXT:    andps {{.*}}, %xmm0
+; SSE2-NEXT:    orps %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: vsel_4xi16:
+; SSSE3:       ## BB#0:
+; SSSE3-NEXT:    andps {{.*}}, %xmm1
+; SSSE3-NEXT:    andps {{.*}}, %xmm0
+; SSSE3-NEXT:    orps %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: vsel_4xi16:
+; SSE41:       ## BB#0:
+; SSE41-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: vsel_4xi16:
+; AVX1:       ## BB#0:
+; AVX1-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: vsel_4xi16:
+; AVX2:       ## BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; AVX2-NEXT:    retq
+  %vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 true>, <4 x i16> %v1, <4 x i16> %v2
+  ret <4 x i16> %vsel
+}
+
 define <4 x i32> @vsel_i32(<4 x i32> %v1, <4 x i32> %v2) {
 ; SSE2-LABEL: vsel_i32:
 ; SSE2:       ## BB#0:
@@ -440,6 +506,57 @@ define <8 x float> @constant_blendvps_avx(<8 x float> %xyzw, <8 x float> %abcd)
   ret <8 x float> %1
 }
 
+define <32 x i8> @constant_pblendvb_avx2(<32 x i8> %xyzw, <32 x i8> %abcd) {
+; SSE2-LABEL: constant_pblendvb_avx2:
+; SSE2:       ## BB#0:
+; SSE2-NEXT:    movaps {{.*#+}} xmm4 = [255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255]
+; SSE2-NEXT:    andps %xmm4, %xmm2
+; SSE2-NEXT:    movaps {{.*#+}} xmm5 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; SSE2-NEXT:    andps %xmm5, %xmm0
+; SSE2-NEXT:    orps %xmm2, %xmm0
+; SSE2-NEXT:    andps %xmm4, %xmm3
+; SSE2-NEXT:    andps %xmm5, %xmm1
+; SSE2-NEXT:    orps %xmm3, %xmm1
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: constant_pblendvb_avx2:
+; SSSE3:       ## BB#0:
+; SSSE3-NEXT:    movaps {{.*#+}} xmm4 = [255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255]
+; SSSE3-NEXT:    andps %xmm4, %xmm2
+; SSSE3-NEXT:    movaps {{.*#+}} xmm5 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; SSSE3-NEXT:    andps %xmm5, %xmm0
+; SSSE3-NEXT:    orps %xmm2, %xmm0
+; SSSE3-NEXT:    andps %xmm4, %xmm3
+; SSSE3-NEXT:    andps %xmm5, %xmm1
+; SSSE3-NEXT:    orps %xmm3, %xmm1
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: constant_pblendvb_avx2:
+; SSE41:       ## BB#0:
+; SSE41-NEXT:    movdqa %xmm0, %xmm4
+; SSE41-NEXT:    movaps {{.*#+}} xmm0 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; SSE41-NEXT:    pblendvb %xmm4, %xmm2
+; SSE41-NEXT:    pblendvb %xmm1, %xmm3
+; SSE41-NEXT:    movdqa %xmm2, %xmm0
+; SSE41-NEXT:    movdqa %xmm3, %xmm1
+; SSE41-NEXT:    retq
+;
+; AVX1-LABEL: constant_pblendvb_avx2:
+; AVX1:       ## BB#0:
+; AVX1-NEXT:    vandps {{.*}}, %ymm1, %ymm1
+; AVX1-NEXT:    vandps {{.*}}, %ymm0, %ymm0
+; AVX1-NEXT:    vorps %ymm1, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: constant_pblendvb_avx2:
+; AVX2:       ## BB#0:
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+  %1 = select <32 x i1> <i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 true, i1 true, i1 true, i1 false>, <32 x i8> %xyzw, <32 x i8> %abcd
+  ret <32 x i8> %1
+}
+
 declare <8 x float> @llvm.x86.avx.blendv.ps.256(<8 x float>, <8 x float>, <8 x float>)
 declare <4 x double> @llvm.x86.avx.blendv.pd.256(<4 x double>, <4 x double>, <4 x double>)