[llvm-branch-commits] [llvm] 01c190e - [AArch64][CostModel]Fix gather scatter cost model

[Caroline Concatto via llvm-branch-commits]

Author: Caroline Concatto
Date: 2021-01-07T14:02:08Z
New Revision: 01c190e907ca4752f7ba2a1390a8c91a48b322d1

URL: https://github.com/llvm/llvm-project/commit/01c190e907ca4752f7ba2a1390a8c91a48b322d1
DIFF: https://github.com/llvm/llvm-project/commit/01c190e907ca4752f7ba2a1390a8c91a48b322d1.diff

LOG: [AArch64][CostModel]Fix gather scatter cost model

This patch fixes a bug introduced in the patch:
https://reviews.llvm.org/D93030

This patch pulls the test for scalable vector to be the first instruction
to be checked. This avoids the Gather and Scatter cost model for AArch64 to
compute the number of vector elements for something that is not a vector and
therefore crashing.

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-gather.ll
    llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-scatter.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index aaf7371c7933..68d382fb784b 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -773,13 +773,13 @@ AArch64TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
 unsigned AArch64TTIImpl::getGatherScatterOpCost(
     unsigned Opcode, Type *DataTy, const Value *Ptr, bool VariableMask,
     Align Alignment, TTI::TargetCostKind CostKind, const Instruction *I) {
+
+  if (!isa<ScalableVectorType>(DataTy))
+    return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
+                                         Alignment, CostKind, I);
   auto *VT = cast<VectorType>(DataTy);
   auto LT = TLI->getTypeLegalizationCost(DL, DataTy);
   ElementCount LegalVF = LT.second.getVectorElementCount();
-  if (!LegalVF.isScalable())
-    return BaseT::getGatherScatterOpCost(Opcode, DataTy, Ptr, VariableMask,
-                                         Alignment, CostKind, I);
-
   Optional<unsigned> MaxNumVScale = getMaxVScale();
   assert(MaxNumVScale && "Expected valid max vscale value");
 

diff  --git a/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-gather.ll b/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-gather.ll
index 38b41b731dd0..83e6ab9932b0 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-gather.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-gather.ll
@@ -32,6 +32,18 @@ define <4 x i32> @masked_gather_v4i32(<4 x i32*> %ld, <4 x i1> %masks, <4 x i32>
   ret <4 x i32> %res
 }
 
+; Check it properly falls back to BasicTTIImpl when legalized MVT is not a vector
+define <1 x i128> @masked_gather_v1i128(<1 x i128*> %ld, <1 x i1> %masks, <1 x i128> %passthru) {
+; CHECK-LABEL: 'masked_gather_v1i128'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction:   %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   ret <1 x i128> %res
+
+  %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
+  ret <1 x i128> %res
+}
+
 declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
 declare <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
 declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 %align, <4 x i1> %masks, <4 x i32> %passthru)
+declare <1 x i128> @llvm.masked.gather.v1i128.v1p0i128(<1 x i128*>, i32, <1 x i1>, <1 x i128>)
+

diff  --git a/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-scatter.ll b/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-scatter.ll
index 4370922e4bf7..fa0002483a1f 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-scatter.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-getIntrinsicInstrCost-scatter.ll
@@ -35,6 +35,17 @@ define void @masked_scatter_v4i32(<4 x i32> %data, <4 x i32*> %ptrs, <4 x i1> %m
   ret void
 }
 
+; Check it properly falls back to BasicTTIImpl when legalized MVT is not a vector
+define void @masked_scatter_v1i128(<1 x i128> %data, <1 x i128*> %ptrs, <1 x i1> %masks) {
+; CHECK-LABEL: 'masked_scatter_v1i128'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction:   call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction:   ret void
+
+  call void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 0, <1 x i1> %masks)
+  ret void
+}
+
 declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks)
 declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x i32*> %ptrs, i32 %align, <vscale x 8 x i1> %masks)
 declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 %align, <4 x i1> %masks)
+declare void @llvm.masked.scatter.v1i128.v1p0i128(<1 x i128> %data, <1 x i128*> %ptrs, i32 %align, <1 x i1> %masks)