[llvm] 187f627 - [ARM] Allow tail predication on sadd_sat and uadd_sat intrinsics
Sam Tebbs via llvm-commits
llvm-commits at lists.llvm.org
Thu Jun 25 03:54:40 PDT 2020
Author: Sam Tebbs
Date: 2020-06-25T11:54:29+01:00
New Revision: 187f627a5057e55e140b2cf8237c69deb87c0193
URL: https://github.com/llvm/llvm-project/commit/187f627a5057e55e140b2cf8237c69deb87c0193
DIFF: https://github.com/llvm/llvm-project/commit/187f627a5057e55e140b2cf8237c69deb87c0193.diff
LOG: [ARM] Allow tail predication on sadd_sat and uadd_sat intrinsics
This patch stops the sadd_sat and uadd_sat intrinsics from blocking tail predication.
Differential revision: https://reviews.llvm.org/D82377
Added:
llvm/test/CodeGen/Thumb2/LowOverheadLoops/tail-pred-intrinsic-add-sat.ll
Modified:
llvm/lib/Target/ARM/MVETailPredication.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/ARM/MVETailPredication.cpp b/llvm/lib/Target/ARM/MVETailPredication.cpp
index 23b35bb44ccf..7af202264348 100644
--- a/llvm/lib/Target/ARM/MVETailPredication.cpp
+++ b/llvm/lib/Target/ARM/MVETailPredication.cpp
@@ -354,8 +354,14 @@ bool MVETailPredication::IsPredicatedVectorLoop() {
return false;
MaskedInsts.push_back(cast<IntrinsicInst>(&I));
} else if (auto *Int = dyn_cast<IntrinsicInst>(&I)) {
- if (Int->getIntrinsicID() == Intrinsic::fma)
- continue;
+ switch (Int->getIntrinsicID()) {
+ case Intrinsic::fma:
+ case Intrinsic::sadd_sat:
+ case Intrinsic::uadd_sat:
+ continue;
+ default:
+ break;
+ }
for (auto &U : Int->args()) {
if (isa<VectorType>(U->getType()))
return false;
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/tail-pred-intrinsic-add-sat.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/tail-pred-intrinsic-add-sat.ll
new file mode 100644
index 000000000000..d405657f4d17
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/tail-pred-intrinsic-add-sat.ll
@@ -0,0 +1,109 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve -verify-machineinstrs -disable-mve-tail-predication=false -o - %s | FileCheck %s
+define arm_aapcs_vfpcc void @uadd_sat(i16* noalias nocapture readonly %pSrcA, i16* noalias nocapture readonly %pSrcB, i16* noalias nocapture %pDst, i32 %blockSize) {
+; CHECK-LABEL: uadd_sat:
+; CHECK: @ %bb.0: @ %entry
+; CHECK-NEXT: .save {r7, lr}
+; CHECK-NEXT: push {r7, lr}
+; CHECK-NEXT: cmp r3, #0
+; CHECK-NEXT: it eq
+; CHECK-NEXT: popeq {r7, pc}
+; CHECK-NEXT: dlstp.16 lr, r3
+; CHECK-NEXT: .LBB0_1: @ %vector.body
+; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vldrh.u16 q0, [r1], #16
+; CHECK-NEXT: vldrh.u16 q1, [r0], #16
+; CHECK-NEXT: vqadd.u16 q0, q1, q0
+; CHECK-NEXT: vstrh.16 q0, [r2], #16
+; CHECK-NEXT: letp lr, .LBB0_1
+; CHECK-NEXT: @ %bb.2: @ %while.end
+; CHECK-NEXT: pop {r7, pc}
+entry:
+ %cmp7 = icmp eq i32 %blockSize, 0
+ br i1 %cmp7, label %while.end, label %vector.ph
+
+vector.ph: ; preds = %entry
+ %n.rnd.up = add i32 %blockSize, 7
+ %n.vec = and i32 %n.rnd.up, -8
+ %trip.count.minus.1 = add i32 %blockSize, -1
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %vector.ph
+ %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+ %next.gep = getelementptr i16, i16* %pSrcA, i32 %index
+ %next.gep20 = getelementptr i16, i16* %pDst, i32 %index
+ %next.gep21 = getelementptr i16, i16* %pSrcB, i32 %index
+ %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %trip.count.minus.1)
+ %0 = bitcast i16* %next.gep to <8 x i16>*
+ %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %0, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
+ %1 = bitcast i16* %next.gep21 to <8 x i16>*
+ %wide.masked.load24 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
+ %2 = call <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16> %wide.masked.load, <8 x i16> %wide.masked.load24)
+ %3 = bitcast i16* %next.gep20 to <8 x i16>*
+ call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %2, <8 x i16>* %3, i32 2, <8 x i1> %active.lane.mask)
+ %index.next = add i32 %index, 8
+ %4 = icmp eq i32 %index.next, %n.vec
+ br i1 %4, label %while.end, label %vector.body
+
+while.end: ; preds = %vector.body, %entry
+ ret void
+}
+
+define arm_aapcs_vfpcc void @sadd_sat(i16* noalias nocapture readonly %pSrcA, i16* noalias nocapture readonly %pSrcB, i16* noalias nocapture %pDst, i32 %blockSize) {
+; CHECK-LABEL: sadd_sat:
+; CHECK: @ %bb.0: @ %entry
+; CHECK-NEXT: .save {r7, lr}
+; CHECK-NEXT: push {r7, lr}
+; CHECK-NEXT: cmp r3, #0
+; CHECK-NEXT: it eq
+; CHECK-NEXT: popeq {r7, pc}
+; CHECK-NEXT: dlstp.16 lr, r3
+; CHECK-NEXT: .LBB1_1: @ %vector.body
+; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT: vldrh.u16 q0, [r1], #16
+; CHECK-NEXT: vldrh.u16 q1, [r0], #16
+; CHECK-NEXT: vqadd.s16 q0, q1, q0
+; CHECK-NEXT: vstrh.16 q0, [r2], #16
+; CHECK-NEXT: letp lr, .LBB1_1
+; CHECK-NEXT: @ %bb.2: @ %while.end
+; CHECK-NEXT: pop {r7, pc}
+entry:
+ %cmp7 = icmp eq i32 %blockSize, 0
+ br i1 %cmp7, label %while.end, label %vector.ph
+
+vector.ph: ; preds = %entry
+ %n.rnd.up = add i32 %blockSize, 7
+ %n.vec = and i32 %n.rnd.up, -8
+ %trip.count.minus.1 = add i32 %blockSize, -1
+ br label %vector.body
+
+vector.body: ; preds = %vector.body, %vector.ph
+ %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+ %next.gep = getelementptr i16, i16* %pSrcA, i32 %index
+ %next.gep20 = getelementptr i16, i16* %pDst, i32 %index
+ %next.gep21 = getelementptr i16, i16* %pSrcB, i32 %index
+ %active.lane.mask = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %trip.count.minus.1)
+ %0 = bitcast i16* %next.gep to <8 x i16>*
+ %wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %0, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
+ %1 = bitcast i16* %next.gep21 to <8 x i16>*
+ %wide.masked.load24 = call <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>* %1, i32 2, <8 x i1> %active.lane.mask, <8 x i16> undef)
+ %2 = call <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16> %wide.masked.load, <8 x i16> %wide.masked.load24)
+ %3 = bitcast i16* %next.gep20 to <8 x i16>*
+ call void @llvm.masked.store.v8i16.p0v8i16(<8 x i16> %2, <8 x i16>* %3, i32 2, <8 x i1> %active.lane.mask)
+ %index.next = add i32 %index, 8
+ %4 = icmp eq i32 %index.next, %n.vec
+ br i1 %4, label %while.end, label %vector.body
+
+while.end: ; preds = %vector.body, %entry
+ ret void
+}
+
+declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
+
+declare <8 x i16> @llvm.masked.load.v8i16.p0v8i16(<8 x i16>*, i32 immarg, <8 x i1>, <8 x i16>)
+
+declare <8 x i16> @llvm.sadd.sat.v8i16(<8 x i16>, <8 x i16>)
+
+declare <8 x i16> @llvm.uadd.sat.v8i16(<8 x i16>, <8 x i16>)
+
+declare void @llvm.masked.store.v8i16.p0v8i16(<8 x i16>, <8 x i16>*, i32 immarg, <8 x i1>)
More information about the llvm-commits
mailing list