[llvm] 1399249 - [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops
Nicholas Guy via llvm-commits
llvm-commits at lists.llvm.org
Wed Jan 5 04:54:37 PST 2022
Author: Nicholas Guy
Date: 2022-01-05T12:54:31Z
New Revision: 13992498cd96dcef34cdf1ff02730d266feb0730
URL: https://github.com/llvm/llvm-project/commit/13992498cd96dcef34cdf1ff02730d266feb0730
DIFF: https://github.com/llvm/llvm-project/commit/13992498cd96dcef34cdf1ff02730d266feb0730.diff
LOG: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops
Differential Revision: https://reviews.llvm.org/D114879
Added:
llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
Modified:
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
llvm/lib/Target/AArch64/AArch64Subtarget.cpp
llvm/lib/Target/AArch64/AArch64Subtarget.h
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 1dfc51b1358d..01e581e81ab8 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -962,6 +962,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
setMinFunctionAlignment(Align(4));
// Set preferred alignments.
setPrefLoopAlignment(Align(1ULL << STI.getPrefLoopLogAlignment()));
+ setMaxBytesForAlignment(STI.getMaxBytesForLoopAlignment());
setPrefFunctionAlignment(Align(1ULL << STI.getPrefFunctionLogAlignment()));
// Only change the limit for entries in a jump table if specified by
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
index f7d3dd0bc222..a5ae7c3a24a8 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.cpp
@@ -157,13 +157,19 @@ void AArch64Subtarget::initializeProperties() {
break;
case NeoverseN1:
PrefFunctionLogAlignment = 4;
+ PrefLoopLogAlignment = 5;
+ MaxBytesForLoopAlignment = 16;
break;
case NeoverseN2:
PrefFunctionLogAlignment = 4;
+ PrefLoopLogAlignment = 5;
+ MaxBytesForLoopAlignment = 16;
VScaleForTuning = 1;
break;
case NeoverseV1:
PrefFunctionLogAlignment = 4;
+ PrefLoopLogAlignment = 5;
+ MaxBytesForLoopAlignment = 16;
VScaleForTuning = 2;
break;
case Neoverse512TVB:
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
index bcd3d873985f..adb10a43769d 100644
--- a/llvm/lib/Target/AArch64/AArch64Subtarget.h
+++ b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -279,6 +279,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
unsigned MaxPrefetchIterationsAhead = UINT_MAX;
unsigned PrefFunctionLogAlignment = 0;
unsigned PrefLoopLogAlignment = 0;
+ unsigned MaxBytesForLoopAlignment = 0;
unsigned MaxJumpTableSize = 0;
unsigned WideningBaseCost = 0;
@@ -470,6 +471,10 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
}
unsigned getPrefLoopLogAlignment() const { return PrefLoopLogAlignment; }
+ unsigned getMaxBytesForLoopAlignment() const {
+ return MaxBytesForLoopAlignment;
+ }
+
unsigned getMaximumJumpTableSize() const { return MaxJumpTableSize; }
unsigned getWideningBaseCost() const { return WideningBaseCost; }
diff --git a/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll b/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
new file mode 100644
index 000000000000..ab3d8494459a
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/aarch64-p2align-max-bytes-neoverse.ll
@@ -0,0 +1,77 @@
+; RUN: llc -mtriple=aarch64-none-linux-gnu -align-loops=32 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-DEFAULT
+; RUN: llc -mtriple=aarch64-none-linux-gnu -mcpu=neoverse-n1 < %s -o -| FileCheck %s --check-prefixes=CHECK,CHECK-N1
+
+define i32 @a(i32 %x, i32* nocapture readonly %y, i32* nocapture readonly %z) {
+; CHECK-DEFAULT: .p2align 5
+; CHECK-N1: .p2align 5, 0x0, 16
+; CHECK-NEXT: .LBB0_5: // %vector.body
+; CHECK-DEFAULT: .p2align 5
+; CHECK-N1: .p2align 5, 0x0, 16
+; CHECK-NEXT: .LBB0_8: // %for.body
+entry:
+ %cmp10 = icmp sgt i32 %x, 0
+ br i1 %cmp10, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader: ; preds = %entry
+ %wide.trip.count = zext i32 %x to i64
+ %min.iters.check = icmp ult i32 %x, 8
+ br i1 %min.iters.check, label %for.body.preheader17, label %vector.ph
+
+vector.ph: ; preds = %for.body.preheader
+ %n.vec = and i64 %wide.trip.count, 4294967288
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %vector.ph
+ %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+ %vec.phi = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %10, %vector.body ]
+ %vec.phi13 = phi <4 x i32> [ zeroinitializer, %vector.ph ], [ %11, %vector.body ]
+ %0 = getelementptr inbounds i32, i32* %y, i64 %index
+ %1 = bitcast i32* %0 to <4 x i32>*
+ %wide.load = load <4 x i32>, <4 x i32>* %1, align 4
+ %2 = getelementptr inbounds i32, i32* %0, i64 4
+ %3 = bitcast i32* %2 to <4 x i32>*
+ %wide.load14 = load <4 x i32>, <4 x i32>* %3, align 4
+ %4 = getelementptr inbounds i32, i32* %z, i64 %index
+ %5 = bitcast i32* %4 to <4 x i32>*
+ %wide.load15 = load <4 x i32>, <4 x i32>* %5, align 4
+ %6 = getelementptr inbounds i32, i32* %4, i64 4
+ %7 = bitcast i32* %6 to <4 x i32>*
+ %wide.load16 = load <4 x i32>, <4 x i32>* %7, align 4
+ %8 = add <4 x i32> %wide.load, %vec.phi
+ %9 = add <4 x i32> %wide.load14, %vec.phi13
+ %10 = add <4 x i32> %8, %wide.load15
+ %11 = add <4 x i32> %9, %wide.load16
+ %index.next = add nuw i64 %index, 8
+ %12 = icmp eq i64 %index.next, %n.vec
+ br i1 %12, label %middle.block, label %vector.body
+
+middle.block: ; preds = %vector.body
+ %bin.rdx = add <4 x i32> %11, %10
+ %13 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %bin.rdx)
+ %cmp.n = icmp eq i64 %n.vec, %wide.trip.count
+ br i1 %cmp.n, label %for.cond.cleanup, label %for.body.preheader17
+
+for.body.preheader17: ; preds = %for.body.preheader, %middle.block
+ %indvars.iv.ph = phi i64 [ 0, %for.body.preheader ], [ %n.vec, %middle.block ]
+ %b.011.ph = phi i32 [ 0, %for.body.preheader ], [ %13, %middle.block ]
+ br label %for.body
+
+for.cond.cleanup: ; preds = %for.body, %middle.block, %entry
+ %b.0.lcssa = phi i32 [ 0, %entry ], [ %13, %middle.block ], [ %add3, %for.body ]
+ ret i32 %b.0.lcssa
+
+for.body: ; preds = %for.body.preheader17, %for.body
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ %indvars.iv.ph, %for.body.preheader17 ]
+ %b.011 = phi i32 [ %add3, %for.body ], [ %b.011.ph, %for.body.preheader17 ]
+ %arrayidx = getelementptr inbounds i32, i32* %y, i64 %indvars.iv
+ %14 = load i32, i32* %arrayidx, align 4
+ %arrayidx2 = getelementptr inbounds i32, i32* %z, i64 %indvars.iv
+ %15 = load i32, i32* %arrayidx2, align 4
+ %add = add i32 %14, %b.011
+ %add3 = add i32 %add, %15
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+ br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)
More information about the llvm-commits
mailing list