[llvm] [AArch64] Enable SVE MaxBW for Neoverse-N2, prefer fixed at same cost (PR #195108)

[via llvm-commits]

llvmorg-github-actions[bot] wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: Graham Hunter (huntergr-arm)

<details>
<summary>Changes</summary>

This should be using the same settings as other 128b SVE cores. Very slight
performance improvement from MaxBW, regressions alleviated by preferring
fixed VFs over scalable when they're the same cost.


---
Full diff: https://github.com/llvm/llvm-project/pull/195108.diff


3 Files Affected:

- (modified) llvm/lib/Target/AArch64/AArch64Processors.td (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/force-scalable-vectorization-always.ll (+1-1) 
- (modified) llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization-cost-tuning.ll (+1-1) 


``````````diff
diff --git a/llvm/lib/Target/AArch64/AArch64Processors.td b/llvm/lib/Target/AArch64/AArch64Processors.td
index 74b2700d08fd1..d7b842a3c9313 100644
--- a/llvm/lib/Target/AArch64/AArch64Processors.td
+++ b/llvm/lib/Target/AArch64/AArch64Processors.td
@@ -690,7 +690,7 @@ def TuneNeoverseN2 : SubtargetFeature<"neoversen2", "ARMProcFamily", "NeoverseN2
                                       FeatureALULSLFast,
                                       FeaturePostRAScheduler,
                                       FeatureEnableSelectOptimize,
-                                      FeatureDisableMaximizeScalableBandwidth,
+                                      FeatureUseFixedOverScalableIfEqualCost,
                                       FeaturePredictableSelectIsExpensive]>;
 
 def TuneNeoverseN3 : SubtargetFeature<"neoversen3", "ARMProcFamily", "NeoverseN3",
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/force-scalable-vectorization-always.ll b/llvm/test/Transforms/LoopVectorize/AArch64/force-scalable-vectorization-always.ll
index c90d00389430d..cb2b67faa2d46 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/force-scalable-vectorization-always.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/force-scalable-vectorization-always.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "Checking a loop in" --filter "Cost for VF" --filter "Final VPlan for" --filter "Selecting VF:" --version 6
-; RUN: opt -passes=loop-vectorize -enable-epilogue-vectorization=false -scalable-vectorization=always -debug-only=loop-vectorize -disable-output %s 2>&1 | FileCheck %s
+; RUN: opt -passes=loop-vectorize -enable-epilogue-vectorization=false -mattr=disable-maximize-scalable-bandwidth -scalable-vectorization=always -debug-only=loop-vectorize -disable-output %s 2>&1 | FileCheck %s
 ; REQUIRES: asserts
 
 target triple = "aarch64"
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization-cost-tuning.ll b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization-cost-tuning.ll
index c1b175f39e852..01749e5453493 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization-cost-tuning.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/scalable-vectorization-cost-tuning.ll
@@ -17,7 +17,7 @@
 
 ; RUN: opt -mtriple=aarch64 -mcpu=neoverse-n2 \
 ; RUN:     -force-target-instruction-cost=1 -passes=loop-vectorize -S -debug-only=loop-vectorize --disable-output < %s 2>&1 \
-; RUN:     | FileCheck %s --check-prefixes=VSCALEFORTUNING1
+; RUN:     | FileCheck %s --check-prefixes=NEOVERSEV2
 
 ; RUN: opt -mtriple=aarch64 -mcpu=neoverse-v2 \
 ; RUN:     -force-target-instruction-cost=1 -passes=loop-vectorize -S -debug-only=loop-vectorize --disable-output < %s 2>&1 \

``````````

</details>


https://github.com/llvm/llvm-project/pull/195108