8 files changed, 164 insertions, 44 deletions
diff --git a/llvm/test/CodeGen/X86/avx-intrinsics-x86-upgrade.ll b/llvm/test/CodeGen/X86/avx-intrinsics-x86-upgrade.ll
new file mode 100644
index 00000000000..d2b44cd64ef
--- /dev/null
+++ b/llvm/test/CodeGen/X86/avx-intrinsics-x86-upgrade.ll
@@ -0,0 +1,26 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7-avx | FileCheck %s
+
+define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
+  ; CHECK: vblendpd
+  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
+  ret <4 x double> %res
+}
+declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
+
+
+define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
+  ; CHECK: vblendps
+  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  ret <8 x float> %res
+}
+declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+
+
+define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
+  ; CHECK: vdpps
+  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  ret <8 x float> %res
+}
+declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+
+
diff --git a/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll b/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
index 7382ddcd740..850d6f2a4a3 100644
--- a/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/avx-intrinsics-x86.ll
@@ -818,18 +818,18 @@ declare <16 x i8> @llvm.x86.sse3.ldu.dq(i8*) nounwind readonly
 
 define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: vblendpd
-  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
   ret <2 x double> %res
 }
-declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vblendps
-  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
@@ -850,35 +850,35 @@ declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x floa
 
 define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: vdppd
-  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
   ret <2 x double> %res
 }
-declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vdpps
-  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: vinsertps
-  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 
 define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
   ; CHECK: vmpsadbw
-  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<8 x i16>> [#uses=1]
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
@@ -899,10 +899,10 @@ declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) noun
 
 define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
   ; CHECK: vpblendw
-  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 7) ; <<8 x i16>> [#uses=1]
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
+declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
@@ -1770,18 +1770,18 @@ declare <8 x float> @llvm.x86.avx.addsub.ps.256(<8 x float>, <8 x float>) nounwi
 
 define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
   ; CHECK: vblendpd
-  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
+  %res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i8 7) ; <<4 x double>> [#uses=1]
   ret <4 x double> %res
 }
-declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
+declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i8) nounwind readnone
 
 
 define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
   ; CHECK: vblendps
-  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  %res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
   ret <8 x float> %res
 }
-declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
 
 
 define <4 x double> @test_x86_avx_blendv_pd_256(<4 x double> %a0, <4 x double> %a1, <4 x double> %a2) {
@@ -1950,10 +1950,10 @@ declare <8 x i32> @llvm.x86.avx.cvtt.ps2dq.256(<8 x float>) nounwind readnone
 
 define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
   ; CHECK: vdpps
-  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
+  %res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i8 7) ; <<8 x float>> [#uses=1]
   ret <8 x float> %res
 }
-declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
+declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i8) nounwind readnone
 
 
 define <4 x double> @test_x86_avx_hadd_pd_256(<4 x double> %a0, <4 x double> %a1) {
diff --git a/llvm/test/CodeGen/X86/avx.ll b/llvm/test/CodeGen/X86/avx.ll
index 6069c14f0d8..cba6d98f5a8 100644
--- a/llvm/test/CodeGen/X86/avx.ll
+++ b/llvm/test/CodeGen/X86/avx.ll
@@ -60,7 +60,7 @@ define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x floa
 ; X32: movl    8(%esp), %ecx
 ; CHECK-NOT: mov
 ;; Try to match a bit more of the instr, since we need the load's offset.
-; CHECK: vinsertps    $192, 12(%{{...}},%{{...}}), %
+; CHECK: vinsertps    $-64, 12(%{{...}},%{{...}}), %
 ; CHECK-NEXT: ret
   %1 = getelementptr inbounds <4 x float>* %pb, i64 %index
   %2 = load <4 x float>* %1, align 16
diff --git a/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll b/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll
new file mode 100644
index 00000000000..ac2c73bb932
--- /dev/null
+++ b/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll
@@ -0,0 +1,33 @@
+; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=core-avx2 -mattr=avx2 | FileCheck %s
+
+define <16 x i16> @test_x86_avx2_pblendw(<16 x i16> %a0, <16 x i16> %a1) {
+  ; CHECK: vpblendw
+  %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+  ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone
+
+
+define <4 x i32> @test_x86_avx2_pblendd_128(<4 x i32> %a0, <4 x i32> %a1) {
+  ; CHECK: vpblendd
+  %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>> [#uses=1]
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone
+
+
+define <8 x i32> @test_x86_avx2_pblendd_256(<8 x i32> %a0, <8 x i32> %a1) {
+  ; CHECK: vpblendd
+  %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>> [#uses=1]
+  ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone
+
+
+define <16 x i16> @test_x86_avx2_mpsadbw(<32 x i8> %a0, <32 x i8> %a1) {
+  ; CHECK: vmpsadbw
+  %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+  ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i32) nounwind readnone
+
diff --git a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
index ab3d591e1d9..31635de3400 100644
--- a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
@@ -475,10 +475,10 @@ declare <4 x i64> @llvm.x86.avx2.movntdqa(i8*) nounwind readonly
 
 define <16 x i16> @test_x86_avx2_mpsadbw(<32 x i8> %a0, <32 x i8> %a1) {
   ; CHECK: vmpsadbw
-  %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+  %res = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %a0, <32 x i8> %a1, i8 7) ; <<16 x i16>> [#uses=1]
   ret <16 x i16> %res
 }
-declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i32) nounwind readnone
+declare <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8>, <32 x i8>, i8) nounwind readnone
 
 
 define <16 x i16> @test_x86_avx2_packusdw(<8 x i32> %a0, <8 x i32> %a1) {
@@ -499,10 +499,10 @@ declare <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8>, <32 x i8>, <32 x i8>) nounw
 
 define <16 x i16> @test_x86_avx2_pblendw(<16 x i16> %a0, <16 x i16> %a1) {
   ; CHECK: vpblendw
-  %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i32 7) ; <<16 x i16>> [#uses=1]
+  %res = call <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16> %a0, <16 x i16> %a1, i8 7) ; <<16 x i16>> [#uses=1]
   ret <16 x i16> %res
 }
-declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i32) nounwind readnone
+declare <16 x i16> @llvm.x86.avx2.pblendw(<16 x i16>, <16 x i16>, i8) nounwind readnone
 
 
 define <32 x i8> @test_x86_avx2_pmaxsb(<32 x i8> %a0, <32 x i8> %a1) {
@@ -706,18 +706,18 @@ declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind re
 
 define <4 x i32> @test_x86_avx2_pblendd_128(<4 x i32> %a0, <4 x i32> %a1) {
   ; CHECK: vpblendd
-  %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i32 7) ; <<4 x i32>> [#uses=1]
+  %res = call <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32> %a0, <4 x i32> %a1, i8 7) ; <<4 x i32>> [#uses=1]
   ret <4 x i32> %res
 }
-declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i32) nounwind readnone
+declare <4 x i32> @llvm.x86.avx2.pblendd.128(<4 x i32>, <4 x i32>, i8) nounwind readnone
 
 
 define <8 x i32> @test_x86_avx2_pblendd_256(<8 x i32> %a0, <8 x i32> %a1) {
   ; CHECK: vpblendd
-  %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i32 7) ; <<8 x i32>> [#uses=1]
+  %res = call <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32> %a0, <8 x i32> %a1, i8 7) ; <<8 x i32>> [#uses=1]
   ret <8 x i32> %res
 }
-declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i32) nounwind readnone
+declare <8 x i32> @llvm.x86.avx2.pblendd.256(<8 x i32>, <8 x i32>, i8) nounwind readnone
 
 
 define <16 x i8> @test_x86_avx2_pbroadcastb_128(<16 x i8> %a0) {
diff --git a/llvm/test/CodeGen/X86/sse41-intrinsics-x86-upgrade.ll b/llvm/test/CodeGen/X86/sse41-intrinsics-x86-upgrade.ll
new file mode 100644
index 00000000000..6fab98e70a8
--- /dev/null
+++ b/llvm/test/CodeGen/X86/sse41-intrinsics-x86-upgrade.ll
@@ -0,0 +1,61 @@
+; RUN: llc < %s -mtriple=i386-apple-darwin -mattr=-avx,+sse4.1 | FileCheck %s
+; This test works just like the non-upgrade one except that it only checks
+; forms which require auto-upgrading.
+
+define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: blendpd
+  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: blendps
+  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
+  ; CHECK: dppd
+  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  ret <2 x double> %res
+}
+declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: dpps
+  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
+  ; CHECK: insertps
+  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
+
+
+
+define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
+  ; CHECK: mpsadbw
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
+
+
+define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
+  ; CHECK: pblendw
+  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
+
+
diff --git a/llvm/test/CodeGen/X86/sse41-intrinsics-x86.ll b/llvm/test/CodeGen/X86/sse41-intrinsics-x86.ll
index 37eff43b28c..5f25a16380d 100644
--- a/llvm/test/CodeGen/X86/sse41-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/sse41-intrinsics-x86.ll
@@ -2,18 +2,18 @@
 
 define <2 x double> @test_x86_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: blendpd
-  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
   ret <2 x double> %res
 }
-declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: blendps
-  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <2 x double> @test_x86_sse41_blendvpd(<2 x double> %a0, <2 x double> %a1, <2 x double> %a2) {
@@ -34,35 +34,35 @@ declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x floa
 
 define <2 x double> @test_x86_sse41_dppd(<2 x double> %a0, <2 x double> %a1) {
   ; CHECK: dppd
-  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i32 7) ; <<2 x double>> [#uses=1]
+  %res = call <2 x double> @llvm.x86.sse41.dppd(<2 x double> %a0, <2 x double> %a1, i8 7) ; <<2 x double>> [#uses=1]
   ret <2 x double> %res
 }
-declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i32) nounwind readnone
+declare <2 x double> @llvm.x86.sse41.dppd(<2 x double>, <2 x double>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_dpps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: dpps
-  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.dpps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.dpps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 define <4 x float> @test_x86_sse41_insertps(<4 x float> %a0, <4 x float> %a1) {
   ; CHECK: insertps
-  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i32 7) ; <<4 x float>> [#uses=1]
+  %res = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
   ret <4 x float> %res
 }
-declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone
+declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
 
 
 
 define <8 x i16> @test_x86_sse41_mpsadbw(<16 x i8> %a0, <16 x i8> %a1) {
   ; CHECK: mpsadbw
-  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %a0, <16 x i8> %a1, i8 7) ; <<8 x i16>> [#uses=1]
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i32) nounwind readnone
+declare <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8>, <16 x i8>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_packusdw(<4 x i32> %a0, <4 x i32> %a1) {
@@ -83,10 +83,10 @@ declare <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8>, <16 x i8>, <16 x i8>) noun
 
 define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
   ; CHECK: pblendw
-  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i32 7) ; <<8 x i16>> [#uses=1]
+  %res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 7) ; <<8 x i16>> [#uses=1]
   ret <8 x i16> %res
 }
-declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i32) nounwind readnone
+declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
 
 
 define <8 x i16> @test_x86_sse41_phminposuw(<8 x i16> %a0) {
diff --git a/llvm/test/CodeGen/X86/sse41.ll b/llvm/test/CodeGen/X86/sse41.ll
index 986488f531e..aa305e2b3cf 100644
--- a/llvm/test/CodeGen/X86/sse41.ll
+++ b/llvm/test/CodeGen/X86/sse41.ll
@@ -618,7 +618,7 @@ define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x floa
 ; X32: movl    8(%esp), %ecx
 ; CHECK-NOT: mov
 ;; Try to match a bit more of the instr, since we need the load's offset.
-; CHECK: insertps    $192, 12(%{{...}},%{{...}}), %
+; CHECK: insertps    $-64, 12(%{{...}},%{{...}}), %
 ; CHECK-NEXT: ret
   %1 = getelementptr inbounds <4 x float>* %pb, i64 %index
   %2 = load <4 x float>* %1, align 16