From ef1ca4d3e965e76d190cdf3c6d6d4f8db67e7a2b Mon Sep 17 00:00:00 2001
From: David Sherwood <david.sherwood@arm.com>
Date: Wed, 12 Jan 2022 09:51:34 +0000
Subject: [PATCH] [AArch64] Fix incorrect use of MVT::getVectorNumElements in
 AArch64TTIImpl::getVectorInstrCost

If we are inserting into or extracting from a scalable vector we do
not know the number of elements at runtime, so we can only let the
index wrap for fixed-length vectors.

Tests added here:

  Analysis/CostModel/AArch64/sve-insert-extract.ll

Differential Revision: https://reviews.llvm.org/D117099
---
 .../AArch64/AArch64TargetTransformInfo.cpp    |  9 ++-
 .../CostModel/AArch64/sve-insert-extract.ll   | 57 +++++++++++++++++++
 .../CostModel/AArch64/sve-intrinsics.ll       |  4 +-
 3 files changed, 65 insertions(+), 5 deletions(-)
 create mode 100644 llvm/test/Analysis/CostModel/AArch64/sve-insert-extract.ll

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 8fd875106b13..0e8c5b820b91 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1594,9 +1594,12 @@ InstructionCost AArch64TTIImpl::getVectorInstrCost(unsigned Opcode, Type *Val,
     if (!LT.second.isVector())
       return 0;
 
-    // The type may be split. Normalize the index to the new type.
-    unsigned Width = LT.second.getVectorNumElements();
-    Index = Index % Width;
+    // The type may be split. For fixed-width vectors we can normalize the
+    // index to the new type.
+    if (LT.second.isFixedLengthVector()) {
+      unsigned Width = LT.second.getVectorNumElements();
+      Index = Index % Width;
+    }
 
     // The element at index zero is already inside the vector.
     if (Index == 0)
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-insert-extract.ll b/llvm/test/Analysis/CostModel/AArch64/sve-insert-extract.ll
new file mode 100644
index 000000000000..a69cb543a3e3
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-insert-extract.ll
@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -cost-model -analyze -S < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+
+define void @ins_el0() #0 {
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v0 = insertelement <vscale x 16 x i8> zeroinitializer, i8 0, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v1 = insertelement <vscale x 8 x i16> zeroinitializer, i16 0, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 0, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v3 = insertelement <vscale x 2 x i64> zeroinitializer, i64 0, i64 0
+  %v0 = insertelement <vscale x 16 x i8> zeroinitializer, i8 0, i64 0
+  %v1 = insertelement <vscale x 8 x i16> zeroinitializer, i16 0, i64 0
+  %v2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 0, i64 0
+  %v3 = insertelement <vscale x 2 x i64> zeroinitializer, i64 0, i64 0
+  ret void
+}
+
+define void @ins_el1() #0 {
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v0 = insertelement <vscale x 16 x i8> zeroinitializer, i8 0, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v1 = insertelement <vscale x 8 x i16> zeroinitializer, i16 0, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 0, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v3 = insertelement <vscale x 2 x i64> zeroinitializer, i64 0, i64 1
+  %v0 = insertelement <vscale x 16 x i8> zeroinitializer, i8 0, i64 1
+  %v1 = insertelement <vscale x 8 x i16> zeroinitializer, i16 0, i64 1
+  %v2 = insertelement <vscale x 4 x i32> zeroinitializer, i32 0, i64 1
+  %v3 = insertelement <vscale x 2 x i64> zeroinitializer, i64 0, i64 1
+  ret void
+}
+
+
+define void @ext_el0() #0 {
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v0 = extractelement <vscale x 16 x i8> zeroinitializer, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v1 = extractelement <vscale x 8 x i16> zeroinitializer, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v2 = extractelement <vscale x 4 x i32> zeroinitializer, i64 0
+; CHECK: Cost Model: Found an estimated cost of 0 for instruction:   %v3 = extractelement <vscale x 2 x i64> zeroinitializer, i64 0
+  %v0 = extractelement <vscale x 16 x i8> zeroinitializer, i64 0
+  %v1 = extractelement <vscale x 8 x i16> zeroinitializer, i64 0
+  %v2 = extractelement <vscale x 4 x i32> zeroinitializer, i64 0
+  %v3 = extractelement <vscale x 2 x i64> zeroinitializer, i64 0
+  ret void
+}
+
+define void @ext_el1() #0 {
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v0 = extractelement <vscale x 16 x i8> zeroinitializer, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v1 = extractelement <vscale x 8 x i16> zeroinitializer, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v2 = extractelement <vscale x 4 x i32> zeroinitializer, i64 1
+; CHECK: Cost Model: Found an estimated cost of 3 for instruction:   %v3 = extractelement <vscale x 2 x i64> zeroinitializer, i64 1
+  %v0 = extractelement <vscale x 16 x i8> zeroinitializer, i64 1
+  %v1 = extractelement <vscale x 8 x i16> zeroinitializer, i64 1
+  %v2 = extractelement <vscale x 4 x i32> zeroinitializer, i64 1
+  %v3 = extractelement <vscale x 2 x i64> zeroinitializer, i64 1
+  ret void
+}
+
+
+attributes #0 = { "target-features"="+sve" vscale_range(1, 16) }
diff --git a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
index 7c4a46c1343b..01c7d87097e1 100644
--- a/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/sve-intrinsics.ll
@@ -3,8 +3,8 @@
 
 define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
 ; CHECK-LABEL: 'vector_insert_extract'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %extract_fixed_from_scalable = call <16 x i32> @llvm.experimental.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 81 for instruction: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.experimental.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.experimental.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.experimental.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void