[X86][AVX512] Use AVX512 attributes instead of -mcpu in vector shift tests

llvm-svn: 312529

llvm/test/CodeGen/X86/vector-shift-ashr-128.ll

@@ -5,10 +5,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; Just one 32-bit run to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=X32-SSE --check-prefix=X32-SSE2
@@ -87,6 +87,7 @@ define <2 x i64> @var_shift_v2i64(<2 x i64> %a, <2 x i64> %b) nounwind {
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpsravq %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: var_shift_v2i64:
@@ -339,6 +340,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQ-NEXT:    vpsravd %ymm1, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovdw %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: var_shift_v8i16:
@@ -347,6 +349,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpsravw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: var_shift_v8i16:
@@ -355,6 +358,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQVL-NEXT:    vpmovsxwd %xmm0, %ymm0
 ; AVX512DQVL-NEXT:    vpsravd %ymm1, %ymm0, %ymm0
 ; AVX512DQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512DQVL-NEXT:    vzeroupper
 ; AVX512DQVL-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: var_shift_v8i16:
@@ -536,6 +540,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovsxbd %xmm0, %zmm0
 ; AVX512-NEXT:    vpsravd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: var_shift_v16i8:
@@ -544,6 +549,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovsxbd %xmm0, %zmm0
 ; AVX512VL-NEXT:    vpsravd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: var_shift_v16i8:
@@ -651,6 +657,7 @@ define <2 x i64> @splatvar_shift_v2i64(<2 x i64> %a, <2 x i64> %b) nounwind {
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpsraq %xmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: splatvar_shift_v2i64:
@@ -951,6 +958,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512-NEXT:    vpsravd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: splatvar_shift_v16i8:
@@ -960,6 +968,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsravd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: splatvar_shift_v16i8:
@@ -1086,6 +1095,7 @@ define <2 x i64> @constant_shift_v2i64(<2 x i64> %a) nounwind {
 ; AVX512-NEXT:    vmovdqa {{.*#+}} xmm1 = [1,7]
 ; AVX512-NEXT:    vpsravq %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: constant_shift_v2i64:
@@ -1262,6 +1272,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512DQ-NEXT:    vpsravd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovdw %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: constant_shift_v8i16:
@@ -1270,6 +1281,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7]
 ; AVX512BW-NEXT:    vpsravw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: constant_shift_v8i16:
@@ -1277,6 +1289,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512DQVL-NEXT:    vpmovsxwd %xmm0, %ymm0
 ; AVX512DQVL-NEXT:    vpsravd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512DQVL-NEXT:    vzeroupper
 ; AVX512DQVL-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: constant_shift_v8i16:
@@ -1439,6 +1452,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512-NEXT:    vpmovsxbd %xmm0, %zmm0
 ; AVX512-NEXT:    vpsravd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: constant_shift_v16i8:
@@ -1446,6 +1460,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512VL-NEXT:    vpmovsxbd %xmm0, %zmm0
 ; AVX512VL-NEXT:    vpsravd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: constant_shift_v16i8:
@@ -1558,6 +1573,7 @@ define <2 x i64> @splatconstant_shift_v2i64(<2 x i64> %a) nounwind {
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512-NEXT:    vpsraq $7, %zmm0, %zmm0
 ; AVX512-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: splatconstant_shift_v2i64:

llvm/test/CodeGen/X86/vector-shift-ashr-256.ll

@@ -3,10 +3,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; 32-bit runs to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=ALL --check-prefix=X32-AVX --check-prefix=X32-AVX1

llvm/test/CodeGen/X86/vector-shift-ashr-512.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
 
 ;
 ; Variable Shifts
@@ -201,14 +201,14 @@ define <64 x i8> @splatvar_shift_v64i8(<64 x i8> %a, <64 x i8> %b) nounwind {
 ; AVX512DQ-NEXT:    vpsraw $2, %ymm0, %ymm5
 ; AVX512DQ-NEXT:    vpaddw %ymm2, %ymm2, %ymm8
 ; AVX512DQ-NEXT:    vpblendvb %ymm8, %ymm5, %ymm0, %ymm0
-; AVX512DQ-NEXT:    vpunpckhbw {{.*#+}} ymm5 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
-; AVX512DQ-NEXT:    vpsraw $4, %ymm5, %ymm9
-; AVX512DQ-NEXT:    vpblendvb %ymm3, %ymm9, %ymm5, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $1, %ymm0, %ymm5
 ; AVX512DQ-NEXT:    vpaddw %ymm8, %ymm8, %ymm9
 ; AVX512DQ-NEXT:    vpblendvb %ymm9, %ymm5, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpackuswb %ymm4, %ymm0, %ymm0
+; AVX512DQ-NEXT:    vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX512DQ-NEXT:    vpsraw $4, %ymm4, %ymm5
+; AVX512DQ-NEXT:    vpblendvb %ymm3, %ymm5, %ymm4, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $2, %ymm3, %ymm4
 ; AVX512DQ-NEXT:    vpblendvb %ymm6, %ymm4, %ymm3, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $1, %ymm3, %ymm4
@@ -328,14 +328,14 @@ define <64 x i8> @constant_shift_v64i8(<64 x i8> %a) nounwind {
 ; AVX512DQ-NEXT:    vpsraw $2, %ymm0, %ymm5
 ; AVX512DQ-NEXT:    vpaddw %ymm2, %ymm2, %ymm8
 ; AVX512DQ-NEXT:    vpblendvb %ymm8, %ymm5, %ymm0, %ymm0
-; AVX512DQ-NEXT:    vpunpckhbw {{.*#+}} ymm5 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
-; AVX512DQ-NEXT:    vpsraw $4, %ymm5, %ymm9
-; AVX512DQ-NEXT:    vpblendvb %ymm3, %ymm9, %ymm5, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $1, %ymm0, %ymm5
 ; AVX512DQ-NEXT:    vpaddw %ymm8, %ymm8, %ymm9
 ; AVX512DQ-NEXT:    vpblendvb %ymm9, %ymm5, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpackuswb %ymm4, %ymm0, %ymm0
+; AVX512DQ-NEXT:    vpunpckhbw {{.*#+}} ymm4 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX512DQ-NEXT:    vpsraw $4, %ymm4, %ymm5
+; AVX512DQ-NEXT:    vpblendvb %ymm3, %ymm5, %ymm4, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $2, %ymm3, %ymm4
 ; AVX512DQ-NEXT:    vpblendvb %ymm6, %ymm4, %ymm3, %ymm3
 ; AVX512DQ-NEXT:    vpsraw $1, %ymm3, %ymm4

llvm/test/CodeGen/X86/vector-shift-lshr-128.ll

@@ -5,10 +5,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; Just one 32-bit run to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=X32-SSE --check-prefix=X32-SSE2
@@ -310,6 +310,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQ-NEXT:    vpsrlvd %ymm1, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovdw %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: var_shift_v8i16:
@@ -318,6 +319,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpsrlvw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: var_shift_v8i16:
@@ -326,6 +328,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
 ; AVX512DQVL-NEXT:    vpsrlvd %ymm1, %ymm0, %ymm0
 ; AVX512DQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512DQVL-NEXT:    vzeroupper
 ; AVX512DQVL-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: var_shift_v8i16:
@@ -456,6 +459,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512-NEXT:    vpsrlvd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: var_shift_v16i8:
@@ -464,6 +468,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsrlvd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: var_shift_v16i8:
@@ -757,6 +762,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512-NEXT:    vpsrlvd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: splatvar_shift_v16i8:
@@ -766,6 +772,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsrlvd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: splatvar_shift_v16i8:
@@ -1024,6 +1031,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512DQ-NEXT:    vpsrlvd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovdw %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: constant_shift_v8i16:
@@ -1032,6 +1040,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7]
 ; AVX512BW-NEXT:    vpsrlvw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: constant_shift_v8i16:
@@ -1039,6 +1048,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512DQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
 ; AVX512DQVL-NEXT:    vpsrlvd {{.*}}(%rip), %ymm0, %ymm0
 ; AVX512DQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512DQVL-NEXT:    vzeroupper
 ; AVX512DQVL-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: constant_shift_v8i16:
@@ -1147,6 +1157,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512-NEXT:    vpsrlvd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: constant_shift_v16i8:
@@ -1154,6 +1165,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsrlvd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: constant_shift_v16i8:

llvm/test/CodeGen/X86/vector-shift-lshr-256.ll

@@ -3,10 +3,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; 32-bit runs to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=ALL --check-prefix=X32-AVX --check-prefix=X32-AVX1
@@ -777,9 +777,9 @@ define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, <32 x i8> %b) nounwind {
 ;
 ; AVX512DQ-LABEL: splatvar_shift_v32i8:
 ; AVX512DQ:       # BB#0:
+; AVX512DQ-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; AVX512DQ-NEXT:    vpsrlw $4, %ymm0, %ymm2
 ; AVX512DQ-NEXT:    vpand {{.*}}(%rip), %ymm2, %ymm2
-; AVX512DQ-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; AVX512DQ-NEXT:    vpsllw $5, %ymm1, %ymm1
 ; AVX512DQ-NEXT:    vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpsrlw $2, %ymm0, %ymm2

llvm/test/CodeGen/X86/vector-shift-lshr-512.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
 
 ;
 ; Variable Shifts

llvm/test/CodeGen/X86/vector-shift-shl-128.ll

@@ -5,10 +5,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; Just one 32-bit run to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=X32-SSE --check-prefix=X32-SSE2
@@ -265,6 +265,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQ-NEXT:    vpsllvd %ymm1, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpmovdw %zmm0, %ymm0
 ; AVX512DQ-NEXT:    # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
+; AVX512DQ-NEXT:    vzeroupper
 ; AVX512DQ-NEXT:    retq
 ;
 ; AVX512BW-LABEL: var_shift_v8i16:
@@ -273,6 +274,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
 ; AVX512BW-NEXT:    vpsllvw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: var_shift_v8i16:
@@ -281,6 +283,7 @@ define <8 x i16> @var_shift_v8i16(<8 x i16> %a, <8 x i16> %b) nounwind {
 ; AVX512DQVL-NEXT:    vpmovzxwd {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
 ; AVX512DQVL-NEXT:    vpsllvd %ymm1, %ymm0, %ymm0
 ; AVX512DQVL-NEXT:    vpmovdw %ymm0, %xmm0
+; AVX512DQVL-NEXT:    vzeroupper
 ; AVX512DQVL-NEXT:    retq
 ;
 ; AVX512BWVL-LABEL: var_shift_v8i16:
@@ -406,6 +409,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512-NEXT:    vpsllvd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: var_shift_v16i8:
@@ -414,6 +418,7 @@ define <16 x i8> @var_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsllvd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: var_shift_v16i8:
@@ -699,6 +704,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512-NEXT:    vpsllvd %zmm1, %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: splatvar_shift_v16i8:
@@ -708,6 +714,7 @@ define <16 x i8> @splatvar_shift_v16i8(<16 x i8> %a, <16 x i8> %b) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero,xmm1[2],zero,zero,zero,xmm1[3],zero,zero,zero,xmm1[4],zero,zero,zero,xmm1[5],zero,zero,zero,xmm1[6],zero,zero,zero,xmm1[7],zero,zero,zero,xmm1[8],zero,zero,zero,xmm1[9],zero,zero,zero,xmm1[10],zero,zero,zero,xmm1[11],zero,zero,zero,xmm1[12],zero,zero,zero,xmm1[13],zero,zero,zero,xmm1[14],zero,zero,zero,xmm1[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsllvd %zmm1, %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: splatvar_shift_v16i8:
@@ -903,6 +910,7 @@ define <8 x i16> @constant_shift_v8i16(<8 x i16> %a) nounwind {
 ; AVX512BW-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,1,2,3,4,5,6,7]
 ; AVX512BW-NEXT:    vpsllvw %zmm1, %zmm0, %zmm0
 ; AVX512BW-NEXT:    # kill: %XMM0<def> %XMM0<kill> %ZMM0<kill>
+; AVX512BW-NEXT:    vzeroupper
 ; AVX512BW-NEXT:    retq
 ;
 ; AVX512DQVL-LABEL: constant_shift_v8i16:
@@ -999,6 +1007,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512-NEXT:    vpsllvd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512-NEXT:    vzeroupper
 ; AVX512-NEXT:    retq
 ;
 ; AVX512VL-LABEL: constant_shift_v16i8:
@@ -1006,6 +1015,7 @@ define <16 x i8> @constant_shift_v16i8(<16 x i8> %a) nounwind {
 ; AVX512VL-NEXT:    vpmovzxbd {{.*#+}} zmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero,xmm0[8],zero,zero,zero,xmm0[9],zero,zero,zero,xmm0[10],zero,zero,zero,xmm0[11],zero,zero,zero,xmm0[12],zero,zero,zero,xmm0[13],zero,zero,zero,xmm0[14],zero,zero,zero,xmm0[15],zero,zero,zero
 ; AVX512VL-NEXT:    vpsllvd {{.*}}(%rip), %zmm0, %zmm0
 ; AVX512VL-NEXT:    vpmovdb %zmm0, %xmm0
+; AVX512VL-NEXT:    vzeroupper
 ; AVX512VL-NEXT:    retq
 ;
 ; X32-SSE-LABEL: constant_shift_v16i8:

llvm/test/CodeGen/X86/vector-shift-shl-256.ll

@@ -3,10 +3,10 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX1
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop,+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=XOP --check-prefix=XOPAVX2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512DQVL
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX512VL --check-prefix=AVX512BWVL
 ;
 ; 32-bit runs to make sure we do reasonable things for i64 shifts.
 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx  | FileCheck %s --check-prefix=ALL --check-prefix=X32-AVX --check-prefix=X32-AVX1
@@ -713,9 +713,9 @@ define <32 x i8> @splatvar_shift_v32i8(<32 x i8> %a, <32 x i8> %b) nounwind {
 ;
 ; AVX512DQ-LABEL: splatvar_shift_v32i8:
 ; AVX512DQ:       # BB#0:
+; AVX512DQ-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; AVX512DQ-NEXT:    vpsllw $4, %ymm0, %ymm2
 ; AVX512DQ-NEXT:    vpand {{.*}}(%rip), %ymm2, %ymm2
-; AVX512DQ-NEXT:    vpbroadcastb %xmm1, %ymm1
 ; AVX512DQ-NEXT:    vpsllw $5, %ymm1, %ymm1
 ; AVX512DQ-NEXT:    vpblendvb %ymm1, %ymm2, %ymm0, %ymm0
 ; AVX512DQ-NEXT:    vpsllw $2, %ymm0, %ymm2

llvm/test/CodeGen/X86/vector-shift-shl-512.ll

@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512dq | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512DQ
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX512 --check-prefix=AVX512BW
 
 ;
 ; Variable Shifts