[llvm] [RISCV][TTI] Properly model odd vector sized LD/ST operations (PR #100436)

Philip Reames via llvm-commits llvm-commits at lists.llvm.org
Wed Jul 24 10:31:59 PDT 2024


https://github.com/preames created https://github.com/llvm/llvm-project/pull/100436

Our actual lowering for these uses RVV instructions.  As a result, the true cost scales with the next largest legal type.  The default implementation assumes that such a type is scalarized resulting in
a much higher cost.  For scalable types which can be promoted (which seems to only happen on zve32x), this would result in an illegal cost being returned spuriously.

>From 95145f528c88a461d169412ef94cb84cae8dce7b Mon Sep 17 00:00:00 2001
From: Philip Reames <preames at rivosinc.com>
Date: Wed, 24 Jul 2024 09:50:33 -0700
Subject: [PATCH] [RISCV][TTI] Properly model odd vector sized LD/ST operations

Our actual lowering for these uses RVV instructions.  As a result, the
true cost scales with the next largest legal type.  The default
implementation assumes that such a type is scalarized.  For scalable
types which can be promoted (which seems to only happen on zve32x),
this would result in an illegal cost being returned spuriously.
---
 .../Target/RISCV/RISCVTargetTransformInfo.cpp | 31 ++++++++++--
 .../CostModel/RISCV/rvv-load-store.ll         | 26 +++++-----
 .../LoopVectorize/RISCV/short-trip-count.ll   | 50 +++++++++----------
 3 files changed, 63 insertions(+), 44 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 5a92d6bab31a9..c110a398bd7f6 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -1390,14 +1390,35 @@ InstructionCost RISCVTTIImpl::getMemoryOpCost(unsigned Opcode, Type *Src,
   InstructionCost Cost = 0;
   if (Opcode == Instruction::Store && OpInfo.isConstant())
     Cost += getStoreImmCost(Src, OpInfo, CostKind);
-  InstructionCost BaseCost =
-    BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
-                           CostKind, OpInfo, I);
+
+  std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Src);
+
+  InstructionCost BaseCost = [&]() {
+    InstructionCost Cost = LT.first;
+    if (CostKind != TTI::TCK_RecipThroughput)
+      return Cost;
+
+    // Our actual lowering uses a VL predicated load of the next legal type.
+    // This is reflected in the result of getTypeLegalizationCost, but
+    // BasicTTI assumes such cases are scalarized.
+    const DataLayout &DL = this->getDataLayout();
+    if (Src->isVectorTy() && LT.second.isVector()) {
+      auto *SrcVT = cast<VectorType>(Src);
+      assert(LT.second.getVectorElementCount() == SrcVT->getElementCount());
+      TypeSize SrcEltSize = DL.getTypeStoreSizeInBits(SrcVT->getElementType());
+      TypeSize LegalEltSize = LT.second.getVectorElementType().getSizeInBits();
+      if (SrcEltSize == LegalEltSize)
+        return Cost;
+    }
+    return BaseT::getMemoryOpCost(Opcode, Src, Alignment, AddressSpace,
+                                  CostKind, OpInfo, I);
+
+  }();
+
   // Assume memory ops cost scale with the number of vector registers
   // possible accessed by the instruction.  Note that BasicTTI already
   // handles the LT.first term for us.
-  if (std::pair<InstructionCost, MVT> LT = getTypeLegalizationCost(Src);
-      LT.second.isVector() && CostKind != TTI::TCK_CodeSize)
+  if (LT.second.isVector() && CostKind != TTI::TCK_CodeSize)
     BaseCost *= TLI->getLMULCost(LT.second);
   return Cost + BaseCost;
 
diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
index 4e92937739d9b..fcc19dfa743f7 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-load-store.ll
@@ -499,16 +499,16 @@ define void @load_oddsize_vectors(ptr %p) {
 ; CHECK-LABEL: 'load_oddsize_vectors'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = load <1 x i32>, ptr %p, align 4
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %2 = load <2 x i32>, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %3 = load <3 x i32>, ptr %p, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %3 = load <3 x i32>, ptr %p, align 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %4 = load <4 x i32>, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %5 = load <5 x i32>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %6 = load <6 x i32>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %7 = load <7 x i32>, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = load <5 x i32>, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = load <6 x i32>, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %7 = load <7 x i32>, ptr %p, align 32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = load <8 x i32>, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 40 for instruction: %9 = load <9 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %10 = load <15 x i32>, ptr %p, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %9 = load <9 x i32>, ptr %p, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = load <15 x i32>, ptr %p, align 64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %11 = load <16 x i32>, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: %12 = load <31 x i32>, ptr %p, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %12 = load <31 x i32>, ptr %p, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %13 = load <32 x i32>, ptr %p, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
@@ -550,15 +550,15 @@ define void @store_oddsize_vectors(ptr %p) {
 ; CHECK-LABEL: 'store_oddsize_vectors'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <1 x i32> undef, ptr %p, align 4
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i32> undef, ptr %p, align 8
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <3 x i32> undef, ptr %p, align 16
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <3 x i32> undef, ptr %p, align 16
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i32> undef, ptr %p, align 16
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: store <5 x i32> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: store <6 x i32> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <7 x i32> undef, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <5 x i32> undef, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <6 x i32> undef, ptr %p, align 32
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <7 x i32> undef, ptr %p, align 32
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <8 x i32> undef, ptr %p, align 32
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: store <15 x i32> undef, ptr %p, align 64
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <15 x i32> undef, ptr %p, align 64
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <16 x i32> undef, ptr %p, align 64
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 256 for instruction: store <31 x i32> undef, ptr %p, align 128
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <31 x i32> undef, ptr %p, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <32 x i32> undef, ptr %p, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
index bce965c723101..bb716d78ca411 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
@@ -7,24 +7,22 @@ define void @small_trip_count_min_vlen_128(ptr nocapture %a) nounwind vscale_ran
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 2
-; CHECK-NEXT:    [[TMP4:%.*]] = sub i32 [[TMP1]], 1
-; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 4, [[TMP4]]
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i32 [[TMP0]], 1
+; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 4, [[TMP1]]
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP0]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i32 [[TMP5]], 2
+; CHECK-NEXT:    [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[INDEX]], 0
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 [[TMP7]], i32 4)
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP7]]
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[TMP8]], i32 0
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i32> poison)
-; CHECK-NEXT:    [[TMP10:%.*]] = add nsw <vscale x 2 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 1, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    call void @llvm.masked.store.nxv2i32.p0(<vscale x 2 x i32> [[TMP10]], ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP3:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32 [[TMP3]], i32 4)
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 1 x i32> @llvm.masked.load.nxv1i32.p0(ptr [[TMP5]], i32 4, <vscale x 1 x i1> [[ACTIVE_LANE_MASK]], <vscale x 1 x i32> poison)
+; CHECK-NEXT:    [[TMP6:%.*]] = add nsw <vscale x 1 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 1 x i32> insertelement (<vscale x 1 x i32> poison, i32 1, i64 0), <vscale x 1 x i32> poison, <vscale x 1 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.store.nxv1i32.p0(<vscale x 1 x i32> [[TMP6]], ptr [[TMP5]], i32 4, <vscale x 1 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP2]]
 ; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
@@ -67,23 +65,23 @@ define void @small_trip_count_min_vlen_32(ptr nocapture %a) nounwind vscale_rang
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i32 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP4:%.*]] = sub i32 [[TMP1]], 1
-; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 4, [[TMP4]]
+; CHECK-NEXT:    [[TMP2:%.*]] = sub i32 [[TMP1]], 1
+; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i32 4, [[TMP2]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[TMP5:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT:    [[TMP6:%.*]] = mul i32 [[TMP5]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[TMP4:%.*]] = mul i32 [[TMP3]], 4
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[INDEX]], 0
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 [[TMP7]], i32 4)
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP7]]
-; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[TMP8]], i32 0
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP9]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
-; CHECK-NEXT:    [[TMP10:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP10]], ptr [[TMP9]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP6]]
+; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 [[TMP5]], i32 4)
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP5]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP7]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[TMP8:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP8]], ptr [[TMP7]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP4]]
 ; CHECK-NEXT:    br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]



More information about the llvm-commits mailing list