From: Martin Storsjö <martin@martin.st>
Date: Sun, 25 Oct 2020 06:35:33 +0000 (+0200)
Subject: Revert "[CostModel] remove cost-kind predicate for vector reduction costs"
X-Git-Tag: llvmorg-13-init~8241
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=1c8371692dfe8245bc6690ff1262dcced4649d21;p=platform%2Fupstream%2Fllvm.git

Revert "[CostModel] remove cost-kind predicate for vector reduction costs"

This reverts commit 22d10b8ab44f703b72b8316a9b3b8adc623ca73f.

This broke compilation e.g. like this:
$ cat synth.c
*a;
float *b;
c() {
  for (;;) {
    float d = -*b * *a++;
    d -= *--b * *a++;
    d -= *--b * *a;
    d -= *--b * *a;
    e(d);
  }
}
$ clang -target x86_64-linux-gnu -c -O2 -ffast-math synth.c
clang: ../include/llvm/Support/Casting.h:104: static bool llvm::isa_impl
_cl<To, const From*>::doit(const From*) [with To = llvm::PointerType; Fr
om = llvm::Type]: Assertion `Val && "isa<> used on a null pointer"' fail
ed.
---

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 87b7041..c615d48 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -1202,6 +1202,9 @@ public:
     case Intrinsic::vector_reduce_fmin:
     case Intrinsic::vector_reduce_umax:
     case Intrinsic::vector_reduce_umin: {
+      // 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(), FMF, 1, I);
       return getTypeBasedIntrinsicInstrCost(Attrs, CostKind);
     }
diff --git a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
index ea9b6a0..bffaa98 100644
--- a/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/ARM/intrinsic-cost-kinds.ll
@@ -213,11 +213,11 @@ define void @reduce_fmax(<16 x float> %va) {
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'reduce_fmax'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 620 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<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 1 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/reduce-add.ll b/llvm/test/Analysis/CostModel/ARM/reduce-add.ll
index b3cc0ad..2564c1e 100644
--- a/llvm/test/Analysis/CostModel/ARM/reduce-add.ll
+++ b/llvm/test/Analysis/CostModel/ARM/reduce-add.ll
@@ -22,19 +22,19 @@ define i32 @reduce_i64(i32 %arg) {
 ; NEON-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'reduce_i64'
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %V2 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %V8 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 66 for instruction: %V16 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; NEON-SIZE-LABEL: 'reduce_i64'
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 29 for instruction: %V4 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %V8 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 103 for instruction: %V16 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
 ; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %V1  = call i64 @llvm.vector.reduce.add.v1i64(<1 x i64> undef)
@@ -67,23 +67,23 @@ define i32 @reduce_i32(i32 %arg) {
 ; NEON-RECIP-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
 ;
 ; V8M-SIZE-LABEL: 'reduce_i32'
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %V2 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 35 for instruction: %V16 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 68 for instruction: %V32 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 133 for instruction: %V64 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
-; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 262 for instruction: %V128 = call i8 @llvm.vector.reduce.add.v128i8(<128 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
+; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = call i8 @llvm.vector.reduce.add.v128i8(<128 x i8> undef)
 ; V8M-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
 ; NEON-SIZE-LABEL: 'reduce_i32'
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V2 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 53 for instruction: %V4 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 150 for instruction: %V8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 391 for instruction: %V16 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 488 for instruction: %V32 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 681 for instruction: %V64 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
-; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1066 for instruction: %V128 = call i8 @llvm.vector.reduce.add.v128i8(<128 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V2 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V4 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V16 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V32 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V64 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
+; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %V128 = call i8 @llvm.vector.reduce.add.v128i8(<128 x i8> undef)
 ; NEON-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
 ;
   %V2   = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
diff --git a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
index 1bedeb7..d3bf703 100644
--- a/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
+++ b/llvm/test/Analysis/CostModel/X86/intrinsic-cost-kinds.ll
@@ -213,11 +213,11 @@ define void @reduce_fmax(<16 x float> %va) {
 ; LATE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
 ;
 ; SIZE-LABEL: 'reduce_fmax'
-; SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<16 x float> %va)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v = call float @llvm.vector.reduce.fmax.v16f32(<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 7 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: %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)