3 files changed, 123 insertions, 91 deletions
diff --git a/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll b/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll
index a30d8371775..36b6da5ef96 100644
--- a/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll
+++ b/llvm/test/CodeGen/X86/avx2-intrinsics-x86-upgrade.ll
@@ -83,3 +83,123 @@ define <4 x i64> @test_x86_avx2_vinserti128(<4 x i64> %a0, <2 x i64> %a1) {
 }
 declare <4 x i64> @llvm.x86.avx2.vinserti128(<4 x i64>, <2 x i64>, i8) nounwind readnone
 
+
+define <4 x double> @test_x86_avx2_vbroadcast_sd_pd_256(<2 x double> %a0) {
+  ; CHECK-LABEL: test_x86_avx2_vbroadcast_sd_pd_256:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vbroadcastsd %xmm0, %ymm0
+  ; CHECK-NEXT:    retl
+  %res = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0)
+  ret <4 x double> %res
+}
+declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
+
+
+define <4 x float> @test_x86_avx2_vbroadcast_ss_ps(<4 x float> %a0) {
+  ; CHECK-LABEL: test_x86_avx2_vbroadcast_ss_ps:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vbroadcastss %xmm0, %xmm0
+  ; CHECK-NEXT:    retl
+  %res = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0)
+  ret <4 x float> %res
+}
+declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
+
+
+define <8 x float> @test_x86_avx2_vbroadcast_ss_ps_256(<4 x float> %a0) {
+  ; CHECK-LABEL: test_x86_avx2_vbroadcast_ss_ps_256:
+  ; CHECK:       ## BB#0:
+  ; CHECK-NEXT:    vbroadcastss %xmm0, %ymm0
+  ; CHECK-NEXT:    retl
+  %res = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0)
+  ret <8 x float> %res
+}
+declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
+
+
+define <16 x i8> @test_x86_avx2_pbroadcastb_128(<16 x i8> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastb_128:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vpbroadcastb %xmm0, %xmm0
+; CHECK-NEXT:    retl
+  %res = call <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8> %a0)
+  ret <16 x i8> %res
+}
+declare <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8>) nounwind readonly
+
+
+define <32 x i8> @test_x86_avx2_pbroadcastb_256(<16 x i8> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastb_256:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vpbroadcastb %xmm0, %ymm0
+; CHECK-NEXT:    retl
+  %res = call <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8> %a0)
+  ret <32 x i8> %res
+}
+declare <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8>) nounwind readonly
+
+
+define <8 x i16> @test_x86_avx2_pbroadcastw_128(<8 x i16> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastw_128:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vpbroadcastw %xmm0, %xmm0
+; CHECK-NEXT:    retl
+  %res = call <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16> %a0)
+  ret <8 x i16> %res
+}
+declare <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16>) nounwind readonly
+
+
+define <16 x i16> @test_x86_avx2_pbroadcastw_256(<8 x i16> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastw_256:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vpbroadcastw %xmm0, %ymm0
+; CHECK-NEXT:    retl
+  %res = call <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16> %a0)
+  ret <16 x i16> %res
+}
+declare <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16>) nounwind readonly
+
+
+define <4 x i32> @test_x86_avx2_pbroadcastd_128(<4 x i32> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastd_128:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vbroadcastss %xmm0, %xmm0
+; CHECK-NEXT:    retl
+  %res = call <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32> %a0)
+  ret <4 x i32> %res
+}
+declare <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32>) nounwind readonly
+
+
+define <8 x i32> @test_x86_avx2_pbroadcastd_256(<4 x i32> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastd_256:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vbroadcastss %xmm0, %ymm0
+; CHECK-NEXT:    retl
+  %res = call <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32> %a0)
+  ret <8 x i32> %res
+}
+declare <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32>) nounwind readonly
+
+
+define <2 x i64> @test_x86_avx2_pbroadcastq_128(<2 x i64> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastq_128:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vpbroadcastq %xmm0, %xmm0
+; CHECK-NEXT:    retl
+  %res = call <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64> %a0)
+  ret <2 x i64> %res
+}
+declare <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64>) nounwind readonly
+
+
+define <4 x i64> @test_x86_avx2_pbroadcastq_256(<2 x i64> %a0) {
+; CHECK-LABEL: test_x86_avx2_pbroadcastq_256:
+; CHECK:       ## BB#0:
+; CHECK-NEXT:    vbroadcastsd %xmm0, %ymm0
+; CHECK-NEXT:    retl
+  %res = call <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64> %a0)
+  ret <4 x i64> %res
+}
+declare <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64>) nounwind readonly
diff --git a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
index 5b607afef91..3b2a009f271 100644
--- a/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
+++ b/llvm/test/CodeGen/X86/avx2-intrinsics-x86.ll
@@ -641,30 +641,6 @@ define <4 x i64> @test_x86_avx2_pmul.dq(<8 x i32> %a0, <8 x i32> %a1) {
 declare <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32>, <8 x i32>) nounwind readnone
 
 
-define <4 x double> @test_x86_avx2_vbroadcast_sd_pd_256(<2 x double> %a0) {
-  ; CHECK: vbroadcastsd
-  %res = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0) ; <<4 x double>> [#uses=1]
-  ret <4 x double> %res
-}
-declare <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double>) nounwind readonly
-
-
-define <4 x float> @test_x86_avx2_vbroadcast_ss_ps(<4 x float> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0) ; <<4 x float>> [#uses=1]
-  ret <4 x float> %res
-}
-declare <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float>) nounwind readonly
-
-
-define <8 x float> @test_x86_avx2_vbroadcast_ss_ps_256(<4 x float> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0) ; <<8 x float>> [#uses=1]
-  ret <8 x float> %res
-}
-declare <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float>) nounwind readonly
-
-
 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, i8 7) ; <<4 x i32>> [#uses=1]
@@ -681,70 +657,6 @@ define <8 x i32> @test_x86_avx2_pblendd_256(<8 x i32> %a0, <8 x i32> %a1) {
 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) {
-  ; CHECK: vpbroadcastb
-  %res = call <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8> %a0) ; <<16 x i8>> [#uses=1]
-  ret <16 x i8> %res
-}
-declare <16 x i8> @llvm.x86.avx2.pbroadcastb.128(<16 x i8>) nounwind readonly
-
-
-define <32 x i8> @test_x86_avx2_pbroadcastb_256(<16 x i8> %a0) {
-  ; CHECK: vpbroadcastb
-  %res = call <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8> %a0) ; <<32 x i8>> [#uses=1]
-  ret <32 x i8> %res
-}
-declare <32 x i8> @llvm.x86.avx2.pbroadcastb.256(<16 x i8>) nounwind readonly
-
-
-define <8 x i16> @test_x86_avx2_pbroadcastw_128(<8 x i16> %a0) {
-  ; CHECK: vpbroadcastw
-  %res = call <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16> %a0) ; <<8 x i16>> [#uses=1]
-  ret <8 x i16> %res
-}
-declare <8 x i16> @llvm.x86.avx2.pbroadcastw.128(<8 x i16>) nounwind readonly
-
-
-define <16 x i16> @test_x86_avx2_pbroadcastw_256(<8 x i16> %a0) {
-  ; CHECK: vpbroadcastw
-  %res = call <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16> %a0) ; <<16 x i16>> [#uses=1]
-  ret <16 x i16> %res
-}
-declare <16 x i16> @llvm.x86.avx2.pbroadcastw.256(<8 x i16>) nounwind readonly
-
-
-define <4 x i32> @test_x86_avx2_pbroadcastd_128(<4 x i32> %a0) {
-  ; CHECK: vbroadcastss
-  %res = call <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32> %a0) ; <<4 x i32>> [#uses=1]
-  ret <4 x i32> %res
-}
-declare <4 x i32> @llvm.x86.avx2.pbroadcastd.128(<4 x i32>) nounwind readonly
-
-
-define <8 x i32> @test_x86_avx2_pbroadcastd_256(<4 x i32> %a0) {
-  ; CHECK: vbroadcastss {{[^,]+}}, %ymm{{[0-9]+}}
-  %res = call <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32> %a0) ; <<8 x i32>> [#uses=1]
-  ret <8 x i32> %res
-}
-declare <8 x i32> @llvm.x86.avx2.pbroadcastd.256(<4 x i32>) nounwind readonly
-
-
-define <2 x i64> @test_x86_avx2_pbroadcastq_128(<2 x i64> %a0) {
-  ; CHECK: vpbroadcastq
-  %res = call <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64> %a0) ; <<2 x i64>> [#uses=1]
-  ret <2 x i64> %res
-}
-declare <2 x i64> @llvm.x86.avx2.pbroadcastq.128(<2 x i64>) nounwind readonly
-
-
-define <4 x i64> @test_x86_avx2_pbroadcastq_256(<2 x i64> %a0) {
-  ; CHECK: vbroadcastsd {{[^,]+}}, %ymm{{[0-9]+}}
-  %res = call <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64> %a0) ; <<4 x i64>> [#uses=1]
-  ret <4 x i64> %res
-}
-declare <4 x i64> @llvm.x86.avx2.pbroadcastq.256(<2 x i64>) nounwind readonly
-
-
 define <8 x i32> @test_x86_avx2_permd(<8 x i32> %a0, <8 x i32> %a1) {
   ; Check that the arguments are swapped between the intrinsic definition
   ; and its lowering. Indeed, the offsets are the first source in
diff --git a/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll b/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
index 03241bbb741..bcfdfc57030 100644
--- a/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
+++ b/llvm/test/CodeGen/X86/stack-folding-int-avx2.ll
@@ -12,7 +12,7 @@ define <4 x double> @stack_fold_broadcastsd_ymm(<2 x double> %a0) {
   ;CHECK-LABEL: stack_fold_broadcastsd_ymm
   ;CHECK:       vbroadcastsd {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
-  %2 = call <4 x double> @llvm.x86.avx2.vbroadcast.sd.pd.256(<2 x double> %a0)
+  %2 = shufflevector <2 x double> %a0, <2 x double> undef, <4 x i32> zeroinitializer
   ; fadd forces execution domain
   %3 = fadd <4 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0>
   ret <4 x double> %3
@@ -23,7 +23,7 @@ define <4 x float> @stack_fold_broadcastss(<4 x float> %a0) {
   ;CHECK-LABEL: stack_fold_broadcastss
   ;CHECK:       vbroadcastss {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
-  %2 = call <4 x float> @llvm.x86.avx2.vbroadcast.ss.ps(<4 x float> %a0)
+  %2 = shufflevector <4 x float> %a0, <4 x float> undef, <4 x i32> zeroinitializer
   ; fadd forces execution domain
   %3 = fadd <4 x float> %2, <float 0x0, float 0x0, float 0x0, float 0x0>
   ret <4 x float> %3
@@ -34,7 +34,7 @@ define <8 x float> @stack_fold_broadcastss_ymm(<4 x float> %a0) {
   ;CHECK-LABEL: stack_fold_broadcastss_ymm
   ;CHECK:       vbroadcastss {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
   %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
-  %2 = call <8 x float> @llvm.x86.avx2.vbroadcast.ss.ps.256(<4 x float> %a0)
+  %2 = shufflevector <4 x float> %a0, <4 x float> undef, <8 x i32> zeroinitializer
   ; fadd forces execution domain
   %3 = fadd <8 x float> %2, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
   ret <8 x float> %3