[X86] Improve costmodel for scalar byte swaps

[lebedev.ri]

Summary

Currently we model i16 bswap as very high cost (10),
which doesn't seem right, with all other being at 1.

Regardless of MOVBE, i16 reg-reg bswap is lowered into
(an extending move plus) rot-by-8:
https://godbolt.org/z/8jrq7fMTj
I think it should at worst have throughput of 1:

Since i32/i64 already have cost of 1,
MOVBE doesn't improve their costs any further.

BUT, MOVBE must have at least a single memory operand, with other being a register.
Which means, if we have a bswap of load, iff load has a single use, we'll fold bswap into load.
Likewise, if we have store of a bswap, iff bswap has a single use, we'll fold bswap into store.
So i think we should treat such a bswap as free.

[craig.topper]

Currently we don't model i16 bswap as very high cost (10),
which doesn't seem right, with all other being at 1.

Was that supposed to say "we model i16 as very high cost(10)" with the don't?

i8 reg-reg

i16 reg-reg?

It looks like i64 BSWAP on Intel Core is 2 uops. Possibly one uop to swap the bytes in the upper and lower halves separately followed by rotate by 32 to exchange the halves.

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

2927

At least on Intel Core CPUs, MOVBE isn't optimized. It's a load or store and a bswap operation. Maybe it's optimized on Atom/Silvermont/Goldmont? It was added to that line of CPU first possibly because those CPUs have been used in networking equipment.

llvm/test/Analysis/CostModel/X86/bswap-store.ll

76

These check lines vanished and were not replaced

113

Same here

llvm/test/Analysis/CostModel/X86/load-bswap.ll

121

And here

llvm/test/Transforms/SLPVectorizer/X86/arith-add-usat.ll

29 ↗

(On Diff #343101)

And here

[RKSimon]

llvm/test/Analysis/CostModel/X86/load-bswap.ll

90

Script being stupid again - you'll need to fix your prefixes

[lebedev.ri]

llvm/test/Analysis/CostModel/X86/load-bswap.ll

90

UGH, i thought i did :(
We need to disable FileCheck strict mode for x86 tests.

[lebedev.ri]

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

2927

Looking at actual AMD Zen3 measurements, movbe r<-m is 1 uop, while movbe m<-r is 2,
which is actually a regression from Zen2/Zen1, as per https://www.agner.org/optimize/instruction_tables.pdf.

As per that table, both are really slow on haswell/broadwell/skylake*,
but fast on Silvermont/Goldmont*/KNL.

So i think we could mark movbe r<-m on AMD's at least.

2927

So i think we could mark movbe r<-m *as free* on AMD's at least.

[lebedev.ri]

Addressing review note - introduce FeatureFastMOVBE, set it on selected CPU models.

[lebedev.ri]

Dumb down check prefixes...

[RKSimon]

Random comment: This has me wishing that we'd made further progress with D46276 - I'd much prefer being able to peer into the scheduler models for costs than relying on yet more feature flags :(

llvm/lib/Target/X86/X86.td

519

You say 'prefer' - is a future intention to alter isel depending on this? I'm not sure that's actually useful.

llvm/test/Transforms/SLPVectorizer/X86/bitreverse.ll

30 ↗

(On Diff #343220)

AVX?

[lebedev.ri]

llvm/lib/Target/X86/X86.td

519

You say 'prefer' - is a future intention to alter isel depending on this?

Not really. I was only interested in doing what is contained in this patch,
i.e. modelling bswap as free in costmodel, if it will be free.

[RKSimon]

llvm/lib/Target/X86/X86.td

519

I guess technically different codegen might still occur if the costs come out slightly different and the vectorizer 'prefers' scalar code - sorry for the noise.

[lebedev.ri]

llvm/lib/Target/X86/X86.td

519

That wasn't noise. "Do you intend to prohibit formation of movbe if not HasFastMOVBE" seems like a good question.
(i do not.)

[lebedev.ri]

In D101924#2741844, @RKSimon wrote:

Random comment: This has me wishing that we'd made further progress with D46276 - I'd much prefer being able to peer into the scheduler models for costs than relying on yet more feature flags :(

I know, right? E.g. even when looking at the most simplest snippet from

In D40008#2716353, @lebedev.ri wrote:

In D40008#2716332, @RKSimon wrote:

In D40008#2715994, @lebedev.ri wrote:

@RKSimon @magabari I'd like to add some more tuples, but i have a question: how are the costs actually derived?
For example, the assembly for interleaved load of i16 w/ stride 2: https://godbolt.org/z/hjb3d5x6E
What's it cost? I'm guessing it's not just 10, aka the instruction count excluding the loads/stores?
Is it 5 from Block RThroughput: 4.8 from MCA: https://godbolt.org/z/fxYcEj3Wx ?
Which CPU should be used for these numbers?

I believe they were taken from IACA probably with a Haswell CPU - a reciprocal throughput from llvm-mca should be similar.

Usually with cost tables we tend to compare numbers from similar spec CPUs (AVX2 - Haswell/Ryzen) and choose the worst.....

I see. So in this case we have:

• znver1/2 4.8 https://godbolt.org/z/W9x6GWdnh https://godbolt.org/z/dx7718YT9 (likely unreliable, awaiting zen3)
• haswell/broadwell/skylake 9 https://godbolt.org/z/bzG17drjn https://godbolt.org/z/frnEfeY6K https://godbolt.org/z/o7jK9M9hK

therefore for that tuple we choose 9, correct? I'm not seeing any other sched models for AVX2 but not AVX512 CPU's.

And another question: now that we've established the rules, should i be submitting these changes through review,
or committing these directly? I fear former would either result in bulky patches that are hard to review,
or saturate the review queue.

... the difference between haswell and zen3 is 3x...
I don't really want to add yet another costmodel subset, but that difference is *NOT* great...

[RKSimon]

llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll

89 ↗

(On Diff #343220)

why are these sat math tests changing?

[lebedev.ri]

Don't forget to check that we are actually looking at ISD::BSWAP

llvm/test/Transforms/SLPVectorizer/X86/arith-add-ssat.ll

89 ↗

(On Diff #343220)

Oops :)

[RKSimon]

LGTM - cheers

[lebedev.ri]

In D101924#2745915, @RKSimon wrote:

LGTM - cheers

Thank you for the review!

llvm/lib/Target/X86/X86.td

: SubtargetFeature<
         "fast-scalar-shift-masks", "HasFastScalarShiftMasks", "true",
         "Prefer a left/right scalar logical shift pair over a shift+and pair">;
 
 def FeatureFastVectorShiftMasks
     : SubtargetFeature<
         "fast-vector-shift-masks", "HasFastVectorShiftMasks", "true",
         "Prefer a left/right vector logical shift pair over a shift+and pair">;
 
+def FeatureFastMOVBE
+    : SubtargetFeature<"fast-movbe", "HasFastMOVBE", "true",
+    "Prefer a movbe over a single-use load + bswap / single-use bswap + store">;
+
 def FeatureUseGLMDivSqrtCosts
     : SubtargetFeature<"use-glm-div-sqrt-costs", "UseGLMDivSqrtCosts", "true",
         "Use Goldmont specific floating point div/sqrt costs">;
 
 // Enable use of alias analysis during code generation.
 def FeatureUseAA : SubtargetFeature<"use-aa", "UseAA", "true",
                                     "Use alias analysis during codegen">;
 
list<SubtargetFeature> SLMAdditionalFeatures = [FeatureSSE42,
                                                   FeatureRDRAND];
   list<SubtargetFeature> SLMTuning = [ProcIntelSLM,
                                       FeatureSlowTwoMemOps,
                                       FeatureSlowLEA,
                                       FeatureSlowIncDec,
                                       FeatureSlowDivide64,
                                       FeatureSlowPMULLD,
                                       FeatureFast7ByteNOP,
+                                      FeatureFastMOVBE,
                                       FeaturePOPCNTFalseDeps,
                                       FeatureInsertVZEROUPPER];
   list<SubtargetFeature> SLMFeatures =
     !listconcat(AtomFeatures, SLMAdditionalFeatures);
 
   // Goldmont
   list<SubtargetFeature> GLMAdditionalFeatures = [FeatureAES,
                                                   FeatureSHA,
                                                   FeatureRDSEED,
                                                   FeatureXSAVE,
                                                   FeatureXSAVEOPT,
                                                   FeatureXSAVEC,
                                                   FeatureXSAVES,
                                                   FeatureCLFLUSHOPT,
                                                   FeatureFSGSBase];
   list<SubtargetFeature> GLMTuning = [FeatureUseGLMDivSqrtCosts,
                                       FeatureSlowTwoMemOps,
                                       FeatureSlowLEA,
                                       FeatureSlowIncDec,
+                                      FeatureFastMOVBE,
                                       FeaturePOPCNTFalseDeps,
                                       FeatureInsertVZEROUPPER];
   list<SubtargetFeature> GLMFeatures =
     !listconcat(SLMFeatures, GLMAdditionalFeatures);
 
   // Goldmont Plus
   list<SubtargetFeature> GLPAdditionalFeatures = [FeaturePTWRITE,
                                                   FeatureRDPID];
   list<SubtargetFeature> GLPTuning = [FeatureUseGLMDivSqrtCosts,
                                       FeatureSlowTwoMemOps,
                                       FeatureSlowLEA,
                                       FeatureSlowIncDec,
+                                      FeatureFastMOVBE,
                                       FeatureInsertVZEROUPPER];
   list<SubtargetFeature> GLPFeatures =
     !listconcat(GLMFeatures, GLPAdditionalFeatures);
 
   // Tremont
   list<SubtargetFeature> TRMAdditionalFeatures = [FeatureCLWB,
                                                   FeatureGFNI];
   list<SubtargetFeature> TRMTuning = GLPTuning;
list<SubtargetFeature> KNLFeatures = [FeatureX87,
                                         FeatureFMA,
                                         FeaturePRFCHW];
   list<SubtargetFeature> KNLTuning = [FeatureSlowDivide64,
                                       FeatureSlow3OpsLEA,
                                       FeatureSlowIncDec,
                                       FeatureSlowTwoMemOps,
                                       FeaturePreferMaskRegisters,
                                       FeatureHasFastGather,
+                                      FeatureFastMOVBE,
                                       FeatureSlowPMADDWD];
   // TODO Add AVX5124FMAPS/AVX5124VNNIW features
   list<SubtargetFeature> KNMFeatures =
     !listconcat(KNLFeatures, [FeatureVPOPCNTDQ]);
 
   // Barcelona
   list<SubtargetFeature> BarcelonaFeatures = [FeatureX87,
                                               FeatureCMPXCHG8B,
list<SubtargetFeature> BtVer2AdditionalFeatures = [FeatureAVX,
                                                      FeatureXSAVE,
                                                      FeatureXSAVEOPT];
   list<SubtargetFeature> BtVer2Tuning = [FeatureFastLZCNT,
                                          FeatureFastBEXTR,
                                          FeatureFastHorizontalOps,
                                          FeatureFast15ByteNOP,
                                          FeatureFastScalarShiftMasks,
                                          FeatureFastVectorShiftMasks,
+                                         FeatureFastMOVBE,
                                          FeatureSlowSHLD];
   list<SubtargetFeature> BtVer2Features =
     !listconcat(BtVer1Features, BtVer2AdditionalFeatures);
 
   // Bulldozer
   list<SubtargetFeature> BdVer1Features = [FeatureX87,
                                            FeatureCMPXCHG8B,
                                            FeatureCMOV,
list<SubtargetFeature> BdVer1Tuning = [FeatureSlowSHLD,
                                          FeatureInsertVZEROUPPER];
 
   // PileDriver
   list<SubtargetFeature> BdVer2AdditionalFeatures = [FeatureF16C,
                                                      FeatureBMI,
                                                      FeatureTBM,
                                                      FeatureFMA,
                                                      FeatureFastBEXTR];
-  list<SubtargetFeature> BdVer2Tuning = BdVer1Tuning;
+  list<SubtargetFeature> BdVer2AdditionalTuning = [FeatureFastMOVBE];
+  list<SubtargetFeature> BdVer2Tuning =
+    !listconcat(BdVer1Tuning, BdVer2AdditionalTuning);
   list<SubtargetFeature> BdVer2Features =
     !listconcat(BdVer1Features, BdVer2AdditionalFeatures);
 
   // Steamroller
   list<SubtargetFeature> BdVer3AdditionalFeatures = [FeatureXSAVEOPT,
                                                      FeatureFSGSBase];
   list<SubtargetFeature> BdVer3Tuning = BdVer2Tuning;
   list<SubtargetFeature> BdVer3Features =
list<SubtargetFeature> ZNFeatures = [FeatureADX,
                                        FeatureXSAVEC,
                                        FeatureXSAVEOPT,
                                        FeatureXSAVES];
   list<SubtargetFeature> ZNTuning = [FeatureFastLZCNT,
                                      FeatureFastBEXTR,
                                      FeatureFast15ByteNOP,
                                      FeatureBranchFusion,
                                      FeatureFastScalarShiftMasks,
+                                     FeatureFastMOVBE,
                                      FeatureSlowSHLD,
                                      FeatureInsertVZEROUPPER];
   list<SubtargetFeature> ZN2AdditionalFeatures = [FeatureCLWB,
                                                   FeatureRDPID,
                                                   FeatureWBNOINVD];
   list<SubtargetFeature> ZN2Tuning = ZNTuning;
   list<SubtargetFeature> ZN2Features =
     !listconcat(ZNFeatures, ZN2AdditionalFeatures);

llvm/lib/Target/X86/X86Subtarget.h

class X86Subtarget final : public X86GenSubtargetInfo {
   bool HasFastHorizontalOps = false;
 
   /// Prefer a left/right scalar logical shifts pair over a shift+and pair.
   bool HasFastScalarShiftMasks = false;
 
   /// Prefer a left/right vector logical shifts pair over a shift+and pair.
   bool HasFastVectorShiftMasks = false;
 
+  /// Prefer a movbe over a single-use load + bswap / single-use bswap + store.
+  bool HasFastMOVBE = false;
+
   /// Use a retpoline thunk rather than indirect calls to block speculative
   /// execution.
   bool UseRetpolineIndirectCalls = false;
 
   /// Use a retpoline thunk or remove any indirect branch to block speculative
   /// execution.
   bool UseRetpolineIndirectBranches = false;
 
public:
   bool hasFastScalarFSQRT() const { return HasFastScalarFSQRT; }
   bool hasFastVectorFSQRT() const { return HasFastVectorFSQRT; }
   bool hasFastLZCNT() const { return HasFastLZCNT; }
   bool hasFastSHLDRotate() const { return HasFastSHLDRotate; }
   bool hasFastBEXTR() const { return HasFastBEXTR; }
   bool hasFastHorizontalOps() const { return HasFastHorizontalOps; }
   bool hasFastScalarShiftMasks() const { return HasFastScalarShiftMasks; }
   bool hasFastVectorShiftMasks() const { return HasFastVectorShiftMasks; }
+  bool hasFastMOVBE() const { return HasFastMOVBE; }
   bool hasMacroFusion() const { return HasMacroFusion; }
   bool hasBranchFusion() const { return HasBranchFusion; }
   bool hasERMSB() const { return HasERMSB; }
   bool hasFSRM() const { return HasFSRM; }
   bool hasSlowDivide32() const { return HasSlowDivide32; }
   bool hasSlowDivide64() const { return HasSlowDivide64; }
   bool padShortFunctions() const { return PadShortFunctions; }
   bool slowTwoMemOps() const { return SlowTwoMemOps; }

llvm/lib/Target/X86/X86TargetTransformInfo.cpp

X86TTIImpl::getTypeBasedIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
   static const CostTblEntry POPCNT32CostTbl[] = { // 32 or 64-bit targets
     { ISD::CTPOP,      MVT::i32,     1 },
     { ISD::CTPOP,      MVT::i16,     1 },
     { ISD::CTPOP,      MVT::i8,      1 },
   };
   static const CostTblEntry X64CostTbl[] = { // 64-bit targets
     { ISD::ABS,        MVT::i64,     2 }, // SUB+CMOV
     { ISD::BITREVERSE, MVT::i64,    14 },
+    { ISD::BSWAP,      MVT::i64,     1 },
     { ISD::CTLZ,       MVT::i64,     4 }, // BSR+XOR or BSR+XOR+CMOV
     { ISD::CTTZ,       MVT::i64,     3 }, // TEST+BSF+CMOV/BRANCH
     { ISD::CTPOP,      MVT::i64,    10 },
     { ISD::SADDO,      MVT::i64,     1 },
     { ISD::UADDO,      MVT::i64,     1 },
     { ISD::UMULO,      MVT::i64,     2 }, // mulq + seto
   };
   static const CostTblEntry X86CostTbl[] = { // 32 or 64-bit targets
     { ISD::ABS,        MVT::i32,     2 }, // SUB+CMOV
     { ISD::ABS,        MVT::i16,     2 }, // SUB+CMOV
     { ISD::BITREVERSE, MVT::i32,    14 },
     { ISD::BITREVERSE, MVT::i16,    14 },
     { ISD::BITREVERSE, MVT::i8,     11 },
+    { ISD::BSWAP,      MVT::i32,     1 },
+    { ISD::BSWAP,      MVT::i16,     1 }, // ROL
     { ISD::CTLZ,       MVT::i32,     4 }, // BSR+XOR or BSR+XOR+CMOV
     { ISD::CTLZ,       MVT::i16,     4 }, // BSR+XOR or BSR+XOR+CMOV
     { ISD::CTLZ,       MVT::i8,      4 }, // BSR+XOR or BSR+XOR+CMOV
     { ISD::CTTZ,       MVT::i32,     3 }, // TEST+BSF+CMOV/BRANCH
     { ISD::CTTZ,       MVT::i16,     3 }, // TEST+BSF+CMOV/BRANCH
     { ISD::CTTZ,       MVT::i8,      3 }, // TEST+BSF+CMOV/BRANCH
     { ISD::CTPOP,      MVT::i32,     8 },
     { ISD::CTPOP,      MVT::i16,     9 },
if (ST->hasPOPCNT()) {
       if (ST->is64Bit())
         if (const auto *Entry = CostTableLookup(POPCNT64CostTbl, ISD, MTy))
           return adjustTableCost(*Entry, LT.first, ICA.getFlags());
 
       if (const auto *Entry = CostTableLookup(POPCNT32CostTbl, ISD, MTy))
         return adjustTableCost(*Entry, LT.first, ICA.getFlags());
     }
 
+    if (ISD == ISD::BSWAP && ST->hasMOVBE() && ST->hasFastMOVBE()) {
+      if (const Instruction *II = ICA.getInst()) {
+        if (II->hasOneUse() && isa<StoreInst>(II->user_back()))
+          return TTI::TCC_Free;
+        if (auto *LI = dyn_cast<LoadInst>(II->getOperand(0))) {
+          if (LI->hasOneUse())
+            return TTI::TCC_Free;
+        }
+      }
+    }
+
     // TODO - add BMI (TZCNT) scalar handling
 
     if (ST->is64Bit())
       if (const auto *Entry = CostTableLookup(X64CostTbl, ISD, MTy))
         return adjustTableCost(*Entry, LT.first, ICA.getFlags());
 
     if (const auto *Entry = CostTableLookup(X86CostTbl, ISD, MTy))
       return adjustTableCost(*Entry, LT.first, ICA.getFlags());

llvm/test/Analysis/CostModel/X86/bswap-store.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X64
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X64
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X86
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X86
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze                           | FileCheck %s --check-prefixes=ALL,X64
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe             | FileCheck %s --check-prefixes=ALL,X64-MOVBE
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe,+fast-movbe | FileCheck %s --check-prefixes=ALL,X64-FASTMOVBE
+
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze                           | FileCheck %s --check-prefixes=ALL,X32
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe             | FileCheck %s --check-prefixes=ALL,X32-MOVBE
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe,+fast-movbe | FileCheck %s --check-prefixes=ALL,X32-FASTMOVBE
 
 declare i16 @llvm.bswap.i16(i16)
 declare i32 @llvm.bswap.i32(i32)
 declare i64 @llvm.bswap.i64(i64)
 declare i128 @llvm.bswap.i128(i128)
 
 define void @var_bswap_store_i16(i16 %a, i16* %dst) {
-; NOMOVBE-LABEL: 'var_bswap_store_i16'
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; MOVBE-LABEL: 'var_bswap_store_i16'
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-LABEL: 'var_bswap_store_i16'
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-MOVBE-LABEL: 'var_bswap_store_i16'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i16'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i16'
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i16'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i16'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i16 @llvm.bswap.i16(i16 %a)
   store i16 %bswap, i16* %dst, align 1
 
   ret void
 }
 define void @var_bswap_store_i16_extrause(i16 %a, i16* %dst) {
-; NOMOVBE-LABEL: 'var_bswap_store_i16_extrause'
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i16 %bswap, 2
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
-;
-; MOVBE-LABEL: 'var_bswap_store_i16_extrause'
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i16 %bswap, 2
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; ALL-LABEL: 'var_bswap_store_i16_extrause'
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %bswap, i16* %dst, align 1
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i16 %bswap, 2
+; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i16 @llvm.bswap.i16(i16 %a)
   store i16 %bswap, i16* %dst, align 1
 
   %bswap2 = shl i16 %bswap, 2 ; incur an extra use to the bswap
 
   ret void
 }
 
 define void @var_bswap_store_i32(i32 %a, i32* %dst) {
-; ALL-LABEL: 'var_bswap_store_i32'
-; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
-; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
-; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-LABEL: 'var_bswap_store_i32'
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-MOVBE-LABEL: 'var_bswap_store_i32'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i32'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i32'
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i32'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i32'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i32 @llvm.bswap.i32(i32 %a)
   store i32 %bswap, i32* %dst, align 1
 
   ret void
 }
 define void @var_bswap_store_i32_extrause(i32 %a, i32* %dst) {
 ; ALL-LABEL: 'var_bswap_store_i32_extrause'
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i32 %bswap, i32* %dst, align 1
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i32 %bswap, 2
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i32 @llvm.bswap.i32(i32 %a)
   store i32 %bswap, i32* %dst, align 1
 
   %bswap2 = shl i32 %bswap, 2 ; incur an extra use to the bswap
 
   ret void
 }
 
 define void @var_bswap_store_i64(i64 %a, i64* %dst) {
 ; X64-LABEL: 'var_bswap_store_i64'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
-; X86-LABEL: 'var_bswap_store_i64'
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-MOVBE-LABEL: 'var_bswap_store_i64'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i64'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i64'
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i64'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i64'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i64 @llvm.bswap.i64(i64 %a)
   store i64 %bswap, i64* %dst, align 1
 
   ret void
 }
 define void @var_bswap_store_i64_extrause(i64 %a, i64* %dst) {
 ; X64-LABEL: 'var_bswap_store_i64_extrause'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i64 %bswap, 2
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
-; X86-LABEL: 'var_bswap_store_i64_extrause'
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i64 %bswap, 2
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-MOVBE-LABEL: 'var_bswap_store_i64_extrause'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i64 %bswap, 2
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i64_extrause'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %bswap, i64* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap2 = shl i64 %bswap, 2
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i64_extrause'
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i64 %bswap, 2
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i64_extrause'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i64 %bswap, 2
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i64_extrause'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %bswap, i64* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i64 %bswap, 2
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i64 @llvm.bswap.i64(i64 %a)
   store i64 %bswap, i64* %dst, align 1
 
   %bswap2 = shl i64 %bswap, 2 ; incur an extra use to the bswap
 
   ret void
 }
 
 define void @var_bswap_store_i128(i128 %a, i128* %dst) {
 ; X64-LABEL: 'var_bswap_store_i128'
-; X64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
-; X86-LABEL: 'var_bswap_store_i128'
-; X86-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-MOVBE-LABEL: 'var_bswap_store_i128'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i128'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i128'
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i128'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i128'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i128 @llvm.bswap.i128(i128 %a)
   store i128 %bswap, i128* %dst, align 1
 
   ret void
 }
 define void @var_bswap_store_i128_extrause(i128 %a, i128* %dst) {
 ; X64-LABEL: 'var_bswap_store_i128_extrause'
-; X64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i128 %bswap, 2
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
-; X86-LABEL: 'var_bswap_store_i128_extrause'
-; X86-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap2 = shl i128 %bswap, 2
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+; X64-MOVBE-LABEL: 'var_bswap_store_i128_extrause'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i128 %bswap, 2
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X64-FASTMOVBE-LABEL: 'var_bswap_store_i128_extrause'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %bswap, i128* %dst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap2 = shl i128 %bswap, 2
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-LABEL: 'var_bswap_store_i128_extrause'
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap2 = shl i128 %bswap, 2
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-MOVBE-LABEL: 'var_bswap_store_i128_extrause'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap2 = shl i128 %bswap, 2
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; X32-FASTMOVBE-LABEL: 'var_bswap_store_i128_extrause'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %bswap, i128* %dst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap2 = shl i128 %bswap, 2
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %bswap = call i128 @llvm.bswap.i128(i128 %a)
   store i128 %bswap, i128* %dst, align 1
 
   %bswap2 = shl i128 %bswap, 2 ; incur an extra use to the bswap
 
   ret void
 }

llvm/test/Analysis/CostModel/X86/bswap.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X64
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X64
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X86
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X86
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,X64
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,X64
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,X86
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,X86
 
 declare i16 @llvm.bswap.i16(i16)
 declare i32 @llvm.bswap.i32(i32)
 declare i64 @llvm.bswap.i64(i64)
 declare i128 @llvm.bswap.i128(i128)
 
 ; Verify the cost of scalar bswap instructions.
 
 define i16 @var_bswap_i16(i16 %a) {
-; NOMOVBE-LABEL: 'var_bswap_i16'
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
-;
-; MOVBE-LABEL: 'var_bswap_i16'
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+; ALL-LABEL: 'var_bswap_i16'
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
 ;
   %bswap = call i16 @llvm.bswap.i16(i16 %a)
   ret i16 %bswap
 }
 
 define i32 @var_bswap_i32(i32 %a) {
 ; ALL-LABEL: 'var_bswap_i32'
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
 ; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
 ;
   %bswap = call i32 @llvm.bswap.i32(i32 %a)
   ret i32 %bswap
 }
 
 define i64 @var_bswap_i64(i64 %a) {
 ; X64-LABEL: 'var_bswap_i64'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
 ; X86-LABEL: 'var_bswap_i64'
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
   %bswap = call i64 @llvm.bswap.i64(i64 %a)
   ret i64 %bswap
 }
 
 define i128 @var_bswap_i128(i128 %a) {
 ; X64-LABEL: 'var_bswap_i128'
-; X64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
 ; X86-LABEL: 'var_bswap_i128'
-; X86-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
   %bswap = call i128 @llvm.bswap.i128(i128 %a)
   ret i128 %bswap
 }

llvm/test/Analysis/CostModel/X86/load-bswap.ll

 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X64
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X64
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=ALL,NOMOVBE,X86
-; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe | FileCheck %s --check-prefixes=ALL,MOVBE,X86
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze                           | FileCheck %s --check-prefixes=ALL,X64
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe             | FileCheck %s --check-prefixes=ALL,X64-MOVBE
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -cost-model -analyze -mattr=+movbe,+fast-movbe | FileCheck %s --check-prefixes=ALL,X64-FASTMOVBE
+
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze                           | FileCheck %s --check-prefixes=ALL,X32
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe             | FileCheck %s --check-prefixes=ALL,X32-MOVBE
+; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -cost-model -analyze -mattr=+movbe,+fast-movbe | FileCheck %s --check-prefixes=ALL,X32-FASTMOVBE
 
 declare i16 @llvm.bswap.i16(i16)
 declare i32 @llvm.bswap.i32(i32)
 declare i64 @llvm.bswap.i64(i64)
 declare i128 @llvm.bswap.i128(i128)
 
 define i16 @var_load_bswap_i16(i16* %src) {
-; NOMOVBE-LABEL: 'var_load_bswap_i16'
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
-;
-; MOVBE-LABEL: 'var_load_bswap_i16'
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+; X64-LABEL: 'var_load_bswap_i16'
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+;
+; X64-MOVBE-LABEL: 'var_load_bswap_i16'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i16'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i16'
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i16'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i16'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
 ;
   %a = load i16, i16* %src, align 1
   %bswap = call i16 @llvm.bswap.i16(i16 %a)
 
   ret i16 %bswap
 }
 define i16 @var_load_bswap_i16_extrause(i16* %src, i16* %clobberdst) {
-; NOMOVBE-LABEL: 'var_load_bswap_i16_extrause'
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i16 %a, 2
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %a2, i16* %clobberdst, align 1
-; NOMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
-;
-; MOVBE-LABEL: 'var_load_bswap_i16_extrause'
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i16 %a, 2
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %a2, i16* %clobberdst, align 1
-; MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
+; ALL-LABEL: 'var_load_bswap_i16_extrause'
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i16, i16* %src, align 1
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i16 @llvm.bswap.i16(i16 %a)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i16 %a, 2
+; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i16 %a2, i16* %clobberdst, align 1
+; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i16 %bswap
 ;
   %a = load i16, i16* %src, align 1
   %bswap = call i16 @llvm.bswap.i16(i16 %a)
 
   %a2 = shl i16 %a, 2 ; incur an extra use to the load
   store i16 %a2, i16* %clobberdst, align 1
 
   ret i16 %bswap
 }
 
 define i32 @var_load_bswap_i32(i32* %src) {
-; ALL-LABEL: 'var_load_bswap_i32'
-; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
-; ALL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
-; ALL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+; X64-LABEL: 'var_load_bswap_i32'
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+;
+; X64-MOVBE-LABEL: 'var_load_bswap_i32'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i32'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i32'
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i32'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i32'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i32, i32* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i32 @llvm.bswap.i32(i32 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 %bswap
 ;
   %a = load i32, i32* %src, align 1
   %bswap = call i32 @llvm.bswap.i32(i32 %a)
 
   ret i32 %bswap
 }
 define i32 @var_load_bswap_i32_extrause(i32* %src, i32* %clobberdst) {
 ; ALL-LABEL: 'var_load_bswap_i32_extrause'

 }
 
 define i64 @var_load_bswap_i64(i64* %src) {
 ; X64-LABEL: 'var_load_bswap_i64'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
-; X86-LABEL: 'var_load_bswap_i64'
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+; X64-MOVBE-LABEL: 'var_load_bswap_i64'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i64'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i64'
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i64'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i64'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
   %a = load i64, i64* %src, align 1
   %bswap = call i64 @llvm.bswap.i64(i64 %a)
 
   ret i64 %bswap
 }
 define i64 @var_load_bswap_i64_extrause(i64* %src, i64* %clobberdst) {
 ; X64-LABEL: 'var_load_bswap_i64_extrause'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i64 %a, 2
 ; X64-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %a2, i64* %clobberdst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
-; X86-LABEL: 'var_load_bswap_i64_extrause'
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i64 %a, 2
-; X86-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %a2, i64* %clobberdst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+; X64-MOVBE-LABEL: 'var_load_bswap_i64_extrause'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i64 %a, 2
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %a2, i64* %clobberdst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i64_extrause'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a = load i64, i64* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %a2 = shl i64 %a, 2
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store i64 %a2, i64* %clobberdst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i64_extrause'
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i64 %a, 2
+; X32-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %a2, i64* %clobberdst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i64_extrause'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i64 %a, 2
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %a2, i64* %clobberdst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i64_extrause'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i64, i64* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i64 @llvm.bswap.i64(i64 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i64 %a, 2
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i64 %a2, i64* %clobberdst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i64 %bswap
 ;
   %a = load i64, i64* %src, align 1
   %bswap = call i64 @llvm.bswap.i64(i64 %a)
 
   %a2 = shl i64 %a, 2 ; incur an extra use to the load
   store i64 %a2, i64* %clobberdst, align 1
 
   ret i64 %bswap
 }
 
 define i128 @var_load_bswap_i128(i128* %src) {
 ; X64-LABEL: 'var_load_bswap_i128'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
-; X64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
-; X86-LABEL: 'var_load_bswap_i128'
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+; X64-MOVBE-LABEL: 'var_load_bswap_i128'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i128'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i128'
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i128'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i128'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
   %a = load i128, i128* %src, align 1
   %bswap = call i128 @llvm.bswap.i128(i128 %a)
 
   ret i128 %bswap
 }
 define i128 @var_load_bswap_i128_extrause(i128* %src, i128* %clobberdst) {
 ; X64-LABEL: 'var_load_bswap_i128_extrause'
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
-; X64-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i128 %a, 2
 ; X64-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %a2, i128* %clobberdst, align 1
 ; X64-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
-; X86-LABEL: 'var_load_bswap_i128_extrause'
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2 = shl i128 %a, 2
-; X86-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %a2, i128* %clobberdst, align 1
-; X86-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+; X64-MOVBE-LABEL: 'var_load_bswap_i128_extrause'
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i128 %a, 2
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %a2, i128* %clobberdst, align 1
+; X64-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X64-FASTMOVBE-LABEL: 'var_load_bswap_i128_extrause'
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a = load i128, i128* %src, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %a2 = shl i128 %a, 2
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store i128 %a2, i128* %clobberdst, align 1
+; X64-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-LABEL: 'var_load_bswap_i128_extrause'
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2 = shl i128 %a, 2
+; X32-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %a2, i128* %clobberdst, align 1
+; X32-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-MOVBE-LABEL: 'var_load_bswap_i128_extrause'
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2 = shl i128 %a, 2
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %a2, i128* %clobberdst, align 1
+; X32-MOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
+;
+; X32-FASTMOVBE-LABEL: 'var_load_bswap_i128_extrause'
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a = load i128, i128* %src, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %bswap = call i128 @llvm.bswap.i128(i128 %a)
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %a2 = shl i128 %a, 2
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store i128 %a2, i128* %clobberdst, align 1
+; X32-FASTMOVBE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i128 %bswap
 ;
   %a = load i128, i128* %src, align 1
   %bswap = call i128 @llvm.bswap.i128(i128 %a)
 
   %a2 = shl i128 %a, 2 ; incur an extra use to the load
   store i128 %a2, i128* %clobberdst, align 1
 
   ret i128 %bswap
 }