[llvm] r275764 - [X86] Add more opcodes to isFrameLoadOpcode/isFrameStoreOpcode. Mainly AVX-512 related.
Craig Topper via llvm-commits
llvm-commits at lists.llvm.org
Sun Jul 17 23:14:40 PDT 2016
Author: ctopper
Date: Mon Jul 18 01:14:39 2016
New Revision: 275764
URL: http://llvm.org/viewvc/llvm-project?rev=275764&view=rev
Log:
[X86] Add more opcodes to isFrameLoadOpcode/isFrameStoreOpcode. Mainly AVX-512 related.
Modified:
llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
llvm/trunk/test/CodeGen/X86/avx512-intel-ocl.ll
llvm/trunk/test/CodeGen/X86/avx512-mask-spills.ll
llvm/trunk/test/CodeGen/X86/avx512-vbroadcast.ll
llvm/trunk/test/CodeGen/X86/avx512vl-vbroadcast.ll
llvm/trunk/test/CodeGen/X86/masked_memop.ll
llvm/trunk/test/CodeGen/X86/unaligned-spill-folding.ll
Modified: llvm/trunk/lib/Target/X86/X86InstrInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86InstrInfo.cpp?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86InstrInfo.cpp (original)
+++ llvm/trunk/lib/Target/X86/X86InstrInfo.cpp Mon Jul 18 01:14:39 2016
@@ -2193,13 +2193,19 @@ static bool isFrameLoadOpcode(int Opcode
case X86::MOVSSrm:
case X86::MOVSDrm:
case X86::MOVAPSrm:
+ case X86::MOVUPSrm:
case X86::MOVAPDrm:
+ case X86::MOVUPDrm:
case X86::MOVDQArm:
+ case X86::MOVDQUrm:
case X86::VMOVSSrm:
case X86::VMOVSDrm:
case X86::VMOVAPSrm:
+ case X86::VMOVUPSrm:
case X86::VMOVAPDrm:
+ case X86::VMOVUPDrm:
case X86::VMOVDQArm:
+ case X86::VMOVDQUrm:
case X86::VMOVUPSYrm:
case X86::VMOVAPSYrm:
case X86::VMOVUPDYrm:
@@ -2208,8 +2214,42 @@ static bool isFrameLoadOpcode(int Opcode
case X86::VMOVDQAYrm:
case X86::MMX_MOVD64rm:
case X86::MMX_MOVQ64rm:
+ case X86::VMOVSSZrm:
+ case X86::VMOVSDZrm:
case X86::VMOVAPSZrm:
+ case X86::VMOVAPSZ128rm:
+ case X86::VMOVAPSZ256rm:
case X86::VMOVUPSZrm:
+ case X86::VMOVUPSZ128rm:
+ case X86::VMOVUPSZ256rm:
+ case X86::VMOVAPDZrm:
+ case X86::VMOVAPDZ128rm:
+ case X86::VMOVAPDZ256rm:
+ case X86::VMOVUPDZrm:
+ case X86::VMOVUPDZ128rm:
+ case X86::VMOVUPDZ256rm:
+ case X86::VMOVDQA32Zrm:
+ case X86::VMOVDQA32Z128rm:
+ case X86::VMOVDQA32Z256rm:
+ case X86::VMOVDQU32Zrm:
+ case X86::VMOVDQU32Z128rm:
+ case X86::VMOVDQU32Z256rm:
+ case X86::VMOVDQA64Zrm:
+ case X86::VMOVDQA64Z128rm:
+ case X86::VMOVDQA64Z256rm:
+ case X86::VMOVDQU64Zrm:
+ case X86::VMOVDQU64Z128rm:
+ case X86::VMOVDQU64Z256rm:
+ case X86::VMOVDQU8Zrm:
+ case X86::VMOVDQU8Z128rm:
+ case X86::VMOVDQU8Z256rm:
+ case X86::VMOVDQU16Zrm:
+ case X86::VMOVDQU16Z128rm:
+ case X86::VMOVDQU16Z256rm:
+ case X86::KMOVBkm:
+ case X86::KMOVWkm:
+ case X86::KMOVDkm:
+ case X86::KMOVQkm:
return true;
}
}
@@ -2225,24 +2265,64 @@ static bool isFrameStoreOpcode(int Opcod
case X86::MOVSSmr:
case X86::MOVSDmr:
case X86::MOVAPSmr:
+ case X86::MOVUPSmr:
case X86::MOVAPDmr:
+ case X86::MOVUPDmr:
case X86::MOVDQAmr:
+ case X86::MOVDQUmr:
case X86::VMOVSSmr:
case X86::VMOVSDmr:
case X86::VMOVAPSmr:
+ case X86::VMOVUPSmr:
case X86::VMOVAPDmr:
+ case X86::VMOVUPDmr:
case X86::VMOVDQAmr:
+ case X86::VMOVDQUmr:
case X86::VMOVUPSYmr:
case X86::VMOVAPSYmr:
case X86::VMOVUPDYmr:
case X86::VMOVAPDYmr:
case X86::VMOVDQUYmr:
case X86::VMOVDQAYmr:
+ case X86::VMOVSSZmr:
+ case X86::VMOVSDZmr:
case X86::VMOVUPSZmr:
+ case X86::VMOVUPSZ128mr:
+ case X86::VMOVUPSZ256mr:
case X86::VMOVAPSZmr:
+ case X86::VMOVAPSZ128mr:
+ case X86::VMOVAPSZ256mr:
+ case X86::VMOVUPDZmr:
+ case X86::VMOVUPDZ128mr:
+ case X86::VMOVUPDZ256mr:
+ case X86::VMOVAPDZmr:
+ case X86::VMOVAPDZ128mr:
+ case X86::VMOVAPDZ256mr:
+ case X86::VMOVDQA32Zmr:
+ case X86::VMOVDQA32Z128mr:
+ case X86::VMOVDQA32Z256mr:
+ case X86::VMOVDQU32Zmr:
+ case X86::VMOVDQU32Z128mr:
+ case X86::VMOVDQU32Z256mr:
+ case X86::VMOVDQA64Zmr:
+ case X86::VMOVDQA64Z128mr:
+ case X86::VMOVDQA64Z256mr:
+ case X86::VMOVDQU64Zmr:
+ case X86::VMOVDQU64Z128mr:
+ case X86::VMOVDQU64Z256mr:
+ case X86::VMOVDQU8Zmr:
+ case X86::VMOVDQU8Z128mr:
+ case X86::VMOVDQU8Z256mr:
+ case X86::VMOVDQU16Zmr:
+ case X86::VMOVDQU16Z128mr:
+ case X86::VMOVDQU16Z256mr:
case X86::MMX_MOVD64mr:
case X86::MMX_MOVQ64mr:
case X86::MMX_MOVNTQmr:
+ case X86::KMOVBmk:
+ case X86::KMOVWmk:
+ case X86::KMOVDmk:
+ case X86::KMOVQmk:
return true;
}
return false;
Modified: llvm/trunk/test/CodeGen/X86/avx512-intel-ocl.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-intel-ocl.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-intel-ocl.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-intel-ocl.ll Mon Jul 18 01:14:39 2016
@@ -69,10 +69,10 @@ define <16 x float> @testf16_regs(<16 x
; WIN64: vmovups {{.*(%rbp).*}}, %zmm21 # 64-byte Reload
; X64-LABEL: test_prolog_epilog
-; X64: kmovq %k7, {{.*}}(%rsp) ## 8-byte Folded Spill
-; X64: kmovq %k6, {{.*}}(%rsp) ## 8-byte Folded Spill
-; X64: kmovq %k5, {{.*}}(%rsp) ## 8-byte Folded Spill
-; X64: kmovq %k4, {{.*}}(%rsp) ## 8-byte Folded Spill
+; X64: kmovq %k7, {{.*}}(%rsp) ## 8-byte Spill
+; X64: kmovq %k6, {{.*}}(%rsp) ## 8-byte Spill
+; X64: kmovq %k5, {{.*}}(%rsp) ## 8-byte Spill
+; X64: kmovq %k4, {{.*}}(%rsp) ## 8-byte Spill
; X64: vmovups %zmm31, {{.*}}(%rsp) ## 64-byte Spill
; X64: vmovups %zmm16, {{.*}}(%rsp) ## 64-byte Spill
; X64: call
Modified: llvm/trunk/test/CodeGen/X86/avx512-mask-spills.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-mask-spills.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-mask-spills.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-mask-spills.ll Mon Jul 18 01:14:39 2016
@@ -9,12 +9,12 @@ define <4 x i1> @test_4i1(<4 x i32> %a,
; CHECK-NEXT: Ltmp0:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vpcmpnleud %xmm1, %xmm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: vpcmpgtd %xmm1, %xmm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: callq _f
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Folded Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Reload
; CHECK-NEXT: korw %k1, %k0, %k0
; CHECK-NEXT: vpmovm2d %k0, %xmm0
; CHECK-NEXT: popq %rax
@@ -34,12 +34,12 @@ define <8 x i1> @test_8i1(<8 x i32> %a,
; CHECK-NEXT: Ltmp1:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vpcmpnleud %ymm1, %ymm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: vpcmpgtd %ymm1, %ymm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: callq _f
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Folded Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Reload
; CHECK-NEXT: korb %k1, %k0, %k0
; CHECK-NEXT: vpmovm2w %k0, %xmm0
; CHECK-NEXT: popq %rax
@@ -59,12 +59,12 @@ define <16 x i1> @test_16i1(<16 x i32> %
; CHECK-NEXT: Ltmp2:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vpcmpnleud %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: vpcmpgtd %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; CHECK-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; CHECK-NEXT: callq _f
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
-; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Folded Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
+; CHECK-NEXT: kmovw {{[0-9]+}}(%rsp), %k1 ## 2-byte Reload
; CHECK-NEXT: korw %k1, %k0, %k0
; CHECK-NEXT: vpmovm2b %k0, %xmm0
; CHECK-NEXT: popq %rax
@@ -83,12 +83,12 @@ define <32 x i1> @test_32i1(<32 x i16> %
; CHECK-NEXT: Ltmp3:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vpcmpnleuw %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovd %k0, {{[0-9]+}}(%rsp) ## 4-byte Folded Spill
+; CHECK-NEXT: kmovd %k0, {{[0-9]+}}(%rsp) ## 4-byte Spill
; CHECK-NEXT: vpcmpgtw %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovd %k0, (%rsp) ## 4-byte Folded Spill
+; CHECK-NEXT: kmovd %k0, (%rsp) ## 4-byte Spill
; CHECK-NEXT: callq _f
-; CHECK-NEXT: kmovd {{[0-9]+}}(%rsp), %k0 ## 4-byte Folded Reload
-; CHECK-NEXT: kmovd (%rsp), %k1 ## 4-byte Folded Reload
+; CHECK-NEXT: kmovd {{[0-9]+}}(%rsp), %k0 ## 4-byte Reload
+; CHECK-NEXT: kmovd (%rsp), %k1 ## 4-byte Reload
; CHECK-NEXT: kord %k1, %k0, %k0
; CHECK-NEXT: vpmovm2b %k0, %ymm0
; CHECK-NEXT: popq %rax
@@ -107,12 +107,12 @@ define <64 x i1> @test_64i1(<64 x i8> %a
; CHECK-NEXT: Ltmp4:
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: vpcmpnleub %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovq %k0, {{[0-9]+}}(%rsp) ## 8-byte Folded Spill
+; CHECK-NEXT: kmovq %k0, {{[0-9]+}}(%rsp) ## 8-byte Spill
; CHECK-NEXT: vpcmpgtb %zmm1, %zmm0, %k0
-; CHECK-NEXT: kmovq %k0, {{[0-9]+}}(%rsp) ## 8-byte Folded Spill
+; CHECK-NEXT: kmovq %k0, {{[0-9]+}}(%rsp) ## 8-byte Spill
; CHECK-NEXT: callq _f
-; CHECK-NEXT: kmovq {{[0-9]+}}(%rsp), %k0 ## 8-byte Folded Reload
-; CHECK-NEXT: kmovq {{[0-9]+}}(%rsp), %k1 ## 8-byte Folded Reload
+; CHECK-NEXT: kmovq {{[0-9]+}}(%rsp), %k0 ## 8-byte Reload
+; CHECK-NEXT: kmovq {{[0-9]+}}(%rsp), %k1 ## 8-byte Reload
; CHECK-NEXT: korq %k1, %k0, %k0
; CHECK-NEXT: vpmovm2b %k0, %zmm0
; CHECK-NEXT: addq $24, %rsp
Modified: llvm/trunk/test/CodeGen/X86/avx512-vbroadcast.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-vbroadcast.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-vbroadcast.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-vbroadcast.ll Mon Jul 18 01:14:39 2016
@@ -411,7 +411,7 @@ define <16 x float> @broadcast_ss_spill(
; ALL-NEXT: .Ltmp0:
; ALL-NEXT: .cfi_def_cfa_offset 16
; ALL-NEXT: vaddss %xmm0, %xmm0, %xmm0
-; ALL-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Folded Spill
+; ALL-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Spill
; ALL-NEXT: callq func_f32
; ALL-NEXT: vbroadcastss {{[0-9]+}}(%rsp), %zmm0 # 4-byte Folded Reload
; ALL-NEXT: popq %rax
@@ -431,7 +431,7 @@ define <8 x double> @broadcast_sd_spill(
; ALL-NEXT: .Ltmp1:
; ALL-NEXT: .cfi_def_cfa_offset 16
; ALL-NEXT: vaddsd %xmm0, %xmm0, %xmm0
-; ALL-NEXT: vmovsd %xmm0, (%rsp) # 8-byte Folded Spill
+; ALL-NEXT: vmovsd %xmm0, (%rsp) # 8-byte Spill
; ALL-NEXT: callq func_f64
; ALL-NEXT: vbroadcastsd (%rsp), %zmm0 # 8-byte Folded Reload
; ALL-NEXT: popq %rax
Modified: llvm/trunk/test/CodeGen/X86/avx512vl-vbroadcast.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512vl-vbroadcast.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512vl-vbroadcast.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512vl-vbroadcast.ll Mon Jul 18 01:14:39 2016
@@ -9,7 +9,7 @@ define <8 x float> @_256_broadcast_ss_sp
; CHECK-NEXT: .Ltmp0:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vaddss %xmm0, %xmm0, %xmm0
-; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Folded Spill
+; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Spill
; CHECK-NEXT: callq func_f32
; CHECK-NEXT: vbroadcastss {{[0-9]+}}(%rsp), %ymm0 # 4-byte Folded Reload
; CHECK-NEXT: popq %rax
@@ -28,7 +28,7 @@ define <4 x float> @_128_broadcast_ss_sp
; CHECK-NEXT: .Ltmp1:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vaddss %xmm0, %xmm0, %xmm0
-; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Folded Spill
+; CHECK-NEXT: vmovss %xmm0, {{[0-9]+}}(%rsp) # 4-byte Spill
; CHECK-NEXT: callq func_f32
; CHECK-NEXT: vbroadcastss {{[0-9]+}}(%rsp), %xmm0 # 4-byte Folded Reload
; CHECK-NEXT: popq %rax
@@ -48,7 +48,7 @@ define <4 x double> @_256_broadcast_sd_s
; CHECK-NEXT: .Ltmp2:
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: vaddsd %xmm0, %xmm0, %xmm0
-; CHECK-NEXT: vmovsd %xmm0, (%rsp) # 8-byte Folded Spill
+; CHECK-NEXT: vmovsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT: callq func_f64
; CHECK-NEXT: vbroadcastsd (%rsp), %ymm0 # 8-byte Folded Reload
; CHECK-NEXT: popq %rax
Modified: llvm/trunk/test/CodeGen/X86/masked_memop.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/masked_memop.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/masked_memop.ll (original)
+++ llvm/trunk/test/CodeGen/X86/masked_memop.ll Mon Jul 18 01:14:39 2016
@@ -4612,7 +4612,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vptestmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: kshiftlw $15, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_2
@@ -4622,7 +4622,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_2: ## %else
; AVX512F-NEXT: kshiftlw $14, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_4
@@ -4632,7 +4632,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_4: ## %else2
; AVX512F-NEXT: kshiftlw $13, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_6
@@ -4642,7 +4642,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_6: ## %else5
; AVX512F-NEXT: kshiftlw $12, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_8
@@ -4652,7 +4652,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_8: ## %else8
; AVX512F-NEXT: kshiftlw $11, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_10
@@ -4662,7 +4662,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_10: ## %else11
; AVX512F-NEXT: kshiftlw $10, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_12
@@ -4672,7 +4672,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_12: ## %else14
; AVX512F-NEXT: kshiftlw $9, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_14
@@ -4682,7 +4682,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_14: ## %else17
; AVX512F-NEXT: kshiftlw $8, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_16
@@ -4692,7 +4692,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_16: ## %else20
; AVX512F-NEXT: kshiftlw $7, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_18
@@ -4702,7 +4702,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_18: ## %else23
; AVX512F-NEXT: kshiftlw $6, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, (%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, (%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_20
@@ -4712,7 +4712,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_20: ## %else26
; AVX512F-NEXT: kshiftlw $5, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_22
@@ -4722,7 +4722,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_22: ## %else29
; AVX512F-NEXT: kshiftlw $4, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_24
@@ -4732,7 +4732,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_24: ## %else32
; AVX512F-NEXT: kshiftlw $3, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_26
@@ -4743,7 +4743,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpmovsxbd %xmm1, %zmm1
; AVX512F-NEXT: kshiftlw $2, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_28
@@ -4754,7 +4754,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpslld $31, %zmm1, %zmm1
; AVX512F-NEXT: kshiftlw $1, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_30
@@ -4765,7 +4765,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k1
; AVX512F-NEXT: kshiftlw $0, %k0, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_32
@@ -4775,7 +4775,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_32: ## %else44
; AVX512F-NEXT: kshiftlw $15, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_34
@@ -4786,7 +4786,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_34: ## %else47
; AVX512F-NEXT: kshiftlw $14, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_36
@@ -4797,7 +4797,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_36: ## %else50
; AVX512F-NEXT: kshiftlw $13, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_38
@@ -4808,7 +4808,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_38: ## %else53
; AVX512F-NEXT: kshiftlw $12, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_40
@@ -4819,7 +4819,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_40: ## %else56
; AVX512F-NEXT: kshiftlw $11, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_42
@@ -4830,7 +4830,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_42: ## %else59
; AVX512F-NEXT: kshiftlw $10, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_44
@@ -4841,7 +4841,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_44: ## %else62
; AVX512F-NEXT: kshiftlw $9, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_46
@@ -4852,7 +4852,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_46: ## %else65
; AVX512F-NEXT: kshiftlw $8, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_48
@@ -4863,7 +4863,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_48: ## %else68
; AVX512F-NEXT: kshiftlw $7, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_50
@@ -4874,7 +4874,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_50: ## %else71
; AVX512F-NEXT: kshiftlw $6, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_52
@@ -4885,7 +4885,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_52: ## %else74
; AVX512F-NEXT: kshiftlw $5, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_54
@@ -4896,7 +4896,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_54: ## %else77
; AVX512F-NEXT: kshiftlw $4, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_56
@@ -4907,7 +4907,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_56: ## %else80
; AVX512F-NEXT: kshiftlw $3, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_58
@@ -4919,7 +4919,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpmovsxbd %xmm2, %zmm1
; AVX512F-NEXT: kshiftlw $2, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_60
@@ -4931,7 +4931,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpslld $31, %zmm1, %zmm1
; AVX512F-NEXT: kshiftlw $1, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_62
@@ -4943,7 +4943,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vptestmd %zmm1, %zmm1, %k0
; AVX512F-NEXT: kshiftlw $0, %k1, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_64
@@ -4954,7 +4954,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_64: ## %else92
; AVX512F-NEXT: kshiftlw $15, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_66
@@ -4964,7 +4964,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_66: ## %else95
; AVX512F-NEXT: kshiftlw $14, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_68
@@ -4974,7 +4974,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_68: ## %else98
; AVX512F-NEXT: kshiftlw $13, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_70
@@ -4984,7 +4984,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_70: ## %else101
; AVX512F-NEXT: kshiftlw $12, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_72
@@ -4994,7 +4994,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_72: ## %else104
; AVX512F-NEXT: kshiftlw $11, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_74
@@ -5004,7 +5004,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_74: ## %else107
; AVX512F-NEXT: kshiftlw $10, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_76
@@ -5014,7 +5014,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_76: ## %else110
; AVX512F-NEXT: kshiftlw $9, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_78
@@ -5024,7 +5024,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_78: ## %else113
; AVX512F-NEXT: kshiftlw $8, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_80
@@ -5034,7 +5034,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_80: ## %else116
; AVX512F-NEXT: kshiftlw $7, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_82
@@ -5044,7 +5044,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_82: ## %else119
; AVX512F-NEXT: kshiftlw $6, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_84
@@ -5054,7 +5054,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_84: ## %else122
; AVX512F-NEXT: kshiftlw $5, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_86
@@ -5064,7 +5064,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_86: ## %else125
; AVX512F-NEXT: kshiftlw $4, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_88
@@ -5074,7 +5074,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_88: ## %else128
; AVX512F-NEXT: kshiftlw $3, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_90
@@ -5085,7 +5085,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpmovsxbd %xmm3, %zmm2
; AVX512F-NEXT: kshiftlw $2, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_92
@@ -5096,7 +5096,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpslld $31, %zmm2, %zmm2
; AVX512F-NEXT: kshiftlw $1, %k0, %k1
; AVX512F-NEXT: kshiftrw $15, %k1, %k1
-; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k1, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k1, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_94
@@ -5107,7 +5107,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vptestmd %zmm2, %zmm2, %k1
; AVX512F-NEXT: kshiftlw $0, %k0, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, {{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_96
@@ -5117,7 +5117,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_96: ## %else140
; AVX512F-NEXT: kshiftlw $15, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_98
@@ -5128,7 +5128,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_98: ## %else143
; AVX512F-NEXT: kshiftlw $14, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_100
@@ -5139,7 +5139,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_100: ## %else146
; AVX512F-NEXT: kshiftlw $13, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_102
@@ -5150,7 +5150,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_102: ## %else149
; AVX512F-NEXT: kshiftlw $12, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_104
@@ -5161,7 +5161,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_104: ## %else152
; AVX512F-NEXT: kshiftlw $11, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_106
@@ -5172,7 +5172,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_106: ## %else155
; AVX512F-NEXT: kshiftlw $10, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_108
@@ -5183,7 +5183,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_108: ## %else158
; AVX512F-NEXT: kshiftlw $9, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_110
@@ -5194,7 +5194,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_110: ## %else161
; AVX512F-NEXT: kshiftlw $8, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_112
@@ -5205,7 +5205,7 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: LBB52_112: ## %else164
; AVX512F-NEXT: kshiftlw $7, %k1, %k0
; AVX512F-NEXT: kshiftrw $15, %k0, %k0
-; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Folded Spill
+; AVX512F-NEXT: kmovw %k0, -{{[0-9]+}}(%rsp) ## 2-byte Spill
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: testb %al, %al
; AVX512F-NEXT: je LBB52_114
@@ -5284,127 +5284,127 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpinsrb $15, 63(%rdi), %xmm2, %xmm2
; AVX512F-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
; AVX512F-NEXT: LBB52_128: ## %else188
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, {{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw (%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw (%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, (%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
; AVX512F-NEXT: kmovw %k2, %eax
@@ -5415,22 +5415,22 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: kmovw %k6, %ebx
; AVX512F-NEXT: kmovw %k7, %r11d
; AVX512F-NEXT: kmovw %k1, %r10d
-; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw -{{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl %eax, -{{[0-9]+}}(%rsp) ## 4-byte Spill
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r8d
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r9d
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %edi
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %esi
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %edx
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %ecx
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %eax
; AVX512F-NEXT: movl -{{[0-9]+}}(%rsp), %r13d ## 4-byte Reload
; AVX512F-NEXT: vmovd %r13d, %xmm2
@@ -5477,28 +5477,28 @@ define <64 x i8> @test_mask_load_64xi8(<
; AVX512F-NEXT: vpinsrb $7, -{{[0-9]+}}(%rsp), %xmm6, %xmm6 ## 4-byte Folded Reload
; AVX512F-NEXT: vpinsrb $8, -{{[0-9]+}}(%rsp), %xmm6, %xmm6 ## 4-byte Folded Reload
; AVX512F-NEXT: vpinsrb $9, {{[0-9]+}}(%rsp), %xmm6, %xmm6 ## 4-byte Folded Reload
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r13d
; AVX512F-NEXT: vpinsrb $10, %r12d, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r12d
; AVX512F-NEXT: vpinsrb $11, %r15d, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r15d
; AVX512F-NEXT: vpinsrb $12, %r14d, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r14d
; AVX512F-NEXT: vpinsrb $13, %ebx, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %ebx
; AVX512F-NEXT: vpinsrb $14, %r11d, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r11d
; AVX512F-NEXT: vpinsrb $15, %r10d, %xmm6, %xmm6
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r10d
; AVX512F-NEXT: vmovd %r8d, %xmm7
-; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Folded Reload
+; AVX512F-NEXT: kmovw {{[0-9]+}}(%rsp), %k0 ## 2-byte Reload
; AVX512F-NEXT: kmovw %k0, %r8d
; AVX512F-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
; AVX512F-NEXT: vpsllw $7, %ymm2, %ymm2
Modified: llvm/trunk/test/CodeGen/X86/unaligned-spill-folding.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/unaligned-spill-folding.ll?rev=275764&r1=275763&r2=275764&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/unaligned-spill-folding.ll (original)
+++ llvm/trunk/test/CodeGen/X86/unaligned-spill-folding.ll Mon Jul 18 01:14:39 2016
@@ -34,7 +34,7 @@ middle.block:
; doesn't force stack realignment though
; UNALIGNED-LABEL: @test1
; UNALIGNED-NOT: andl $-{{..}}, %esp
-; UNALIGNED: movdqu {{.*}} # 16-byte Folded Spill
+; UNALIGNED: movdqu {{.*}} # 16-byte Spill
; UNALIGNED-NOT: paddd {{.*}} # 16-byte Folded Reload
; ALIGNED-LABEL: @test1
More information about the llvm-commits
mailing list