[ARM] remove cost-kind predicate for cmp/sel costs

This is the cmp/sel sibling to D90692.
Again, the reasoning is: the throughput cost is number of instructions/uops,
so size/blended costs are identical except in special cases (for example,
fdiv or other known-expensive machine instructions or things like MVE that
may require cracking into >1 uops).

We need to check for a valid (non-null) condition type parameter because
SimplifyCFG may pass nullptr for that (and so we will crash multiple
regression tests without that check). I'm not sure if passing nullptr makes
sense, but other code in the cost model does appear to check if that param
is set or not.

Differential Revision: https://reviews.llvm.org/D90781

diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 04c4e18..d36e70f 100644 (file)
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -839,12 +839,8 @@ int ARMTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
     return Cost;
   }
 
-  if (CostKind != TTI::TCK_RecipThroughput)
-    return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind,
-                                     I);
-
   // On NEON a vector select gets lowered to vbsl.
-  if (ST->hasNEON() && ValTy->isVectorTy() && ISD == ISD::SELECT) {
+  if (ST->hasNEON() && ValTy->isVectorTy() && ISD == ISD::SELECT && CondTy) {
     // Lowering of some vector selects is currently far from perfect.
     static const TypeConversionCostTblEntry NEONVectorSelectTbl[] = {
       { ISD::SELECT, MVT::v4i1, MVT::v4i64, 4*4 + 1*2 + 1 },
@@ -865,9 +861,13 @@ int ARMTTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
     return LT.first;
   }
 
-  int BaseCost = ST->hasMVEIntegerOps() && ValTy->isVectorTy()
-                     ? ST->getMVEVectorCostFactor()
-                     : 1;
+  // Default to cheap (throughput/size of 1 instruction) but adjust throughput
+  // for "multiple beats" potentially needed by MVE instructions.
+  int BaseCost = 1;
+  if (CostKind != TTI::TCK_CodeSize && ST->hasMVEIntegerOps() &&
+      ValTy->isVectorTy())
+    BaseCost = ST->getMVEVectorCostFactor();
+
   return BaseCost *
          BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, VecPred, CostKind, I);
 }

diff --git a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
index 40ff13f..4e18aca 100644 (file)
--- a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
@@ -153,7 +153,7 @@ define void @fshl(i32 %a, i32 %b, i32 %c, <16 x i32> %va, <16 x i32> %vb, <16 x
 ;
 ; SIZE_LATE-LABEL: 'fshl'
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 562 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 564 for instruction: %v = call <16 x i32> @llvm.fshl.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i32> %vc)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %s = call i32 @llvm.fshl.i32(i32 %a, i32 %b, i32 %c)
@@ -217,7 +217,7 @@ define void @reduce_fmax(<16 x float> %va) {
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'reduce_fmax'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 620 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 628 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)

diff --git a/llvm/test/Analysis/CostModel/ARM/select.ll b/llvm/test/Analysis/CostModel/ARM/select.ll
index 2c5f893..67a5580 100644 (file)
--- a/llvm/test/Analysis/CostModel/ARM/select.ll
+++ b/llvm/test/Analysis/CostModel/ARM/select.ll
@@ -185,21 +185,21 @@ define void @selects() {
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v11 = select <2 x i1> undef, <2 x i16> undef, <2 x i16> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v12 = select <4 x i1> undef, <4 x i16> undef, <4 x i16> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v13 = select <8 x i1> undef, <8 x i16> undef, <8 x i16> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v13b = select <16 x i1> undef, <16 x i16> undef, <16 x i16> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v14 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v15 = select <4 x i1> undef, <4 x i32> undef, <4 x i32> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v15b = select <8 x i1> undef, <8 x i32> undef, <8 x i32> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v15c = select <16 x i1> undef, <16 x i32> undef, <16 x i32> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16 = select <2 x i1> undef, <2 x i64> undef, <2 x i64> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %v16a = select <4 x i1> undef, <4 x i64> undef, <4 x i64> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 50 for instruction: %v16b = select <8 x i1> undef, <8 x i64> undef, <8 x i64> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 100 for instruction: %v16c = select <16 x i1> undef, <16 x i64> undef, <16 x i64> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v17 = select <2 x i1> undef, <2 x float> undef, <2 x float> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v18 = select <4 x i1> undef, <4 x float> undef, <4 x float> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v19 = select <2 x i1> undef, <2 x double> undef, <2 x double> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v20 = select <1 x i1> undef, <1 x i32> undef, <1 x i32> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v21 = select <3 x i1> undef, <3 x float> undef, <3 x float> undef
-; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v22 = select <5 x i1> undef, <5 x double> undef, <5 x double> undef
+; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v22 = select <5 x i1> undef, <5 x double> undef, <5 x double> undef
 ; CHECK-NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; CHECK-THUMB1-SIZE-LABEL: 'selects'