[CostModel] remove cost-kind predicate for FP add/mul vector reduction costs

This was originally part of:
f2c25c70791d
but that was reverted because there was an underlying bug in
processing the vector type of these intrinsics. That was
fixed with:
74ffc823ed21

This is similar in spirit to 01ea93d85d6e (memcpy) except that
here the underlying caller assumptions were created for vectorizer
use (throughput) rather than other passes.

That meant targets could have an enormous throughput cost with no
corresponding size, latency, or blended cost increase.

Paraphrasing from the previous commits:
This may not make sense for some callers, but at least now the
costs will be consistently wrong instead of mysteriously wrong.

Targets should provide better overrides if the current modeling
is not accurate.

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index d4c4aa2..5402da6 100644 (file)
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1205,11 +1205,8 @@ public:
     }
     case Intrinsic::vector_reduce_fadd:
     case Intrinsic::vector_reduce_fmul: {
-      // FIXME: all cost kinds should default to the same thing?
-      if (CostKind != TTI::TCK_RecipThroughput)
-        return BaseT::getIntrinsicInstrCost(ICA, CostKind);
       IntrinsicCostAttributes Attrs(
-        IID, RetTy, {Args[0]->getType(), Args[1]->getType()}, FMF, 1, I);
+          IID, RetTy, {Args[0]->getType(), Args[1]->getType()}, FMF, 1, I);
       return getTypeBasedIntrinsicInstrCost(Attrs, CostKind);
     }
     case Intrinsic::fshl:

diff --git a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
index 4671325..c477019 100644 (file)
--- a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
@@ -236,11 +236,11 @@ define void @reduce_fmul(<16 x float> %va) {
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'reduce_fmul'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call float @llvm.vector.reduce.fmul.v16f32(float 4.200000e+01, <16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v = call float @llvm.vector.reduce.fmul.v16f32(float 4.200000e+01, <16 x float> %va)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'reduce_fmul'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call float @llvm.vector.reduce.fmul.v16f32(float 4.200000e+01, <16 x float> %va)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v = call float @llvm.vector.reduce.fmul.v16f32(float 4.200000e+01, <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.fmul.v16f32(float 42.0, <16 x float> %va)
@@ -257,11 +257,11 @@ define void @reduce_fadd_fast(<16 x float> %va) {
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'reduce_fadd_fast'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> %va)
 ; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE_LATE-LABEL: 'reduce_fadd_fast'
-; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> %va)
+; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.000000e+00, <16 x float> %va)
 ; SIZE_LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
   %v = call fast float @llvm.vector.reduce.fadd.v16f32(float 0.0, <16 x float> %va)