[AArch64][SME]: Scalarize masked gather/scatter in streaming mode.

Add testing files:
 - streaming-compatible-expand-masked-gather-scatter.ll

Reviewed By: david-arm, sdesmalen

Differential Revision: https://reviews.llvm.org/D138588

diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
index 7db2a60..e9a2286 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -259,7 +259,7 @@ public:
   }
 
   bool isLegalMaskedGatherScatter(Type *DataType) const {
-    if (!ST->hasSVE())
+    if (!ST->hasSVE() || ST->forceStreamingCompatibleSVE())
       return false;
 
     // For fixed vectors, scalarize if not using SVE for them.

diff --git a/llvm/test/Transforms/ScalarizeMaskedMemIntrin/AArch64/streaming-compatible-expand-masked-gather-scatter.ll b/llvm/test/Transforms/ScalarizeMaskedMemIntrin/AArch64/streaming-compatible-expand-masked-gather-scatter.ll
new file mode 100644 (file)
index 0000000..b0adcb8
--- /dev/null
+++ b/llvm/test/Transforms/ScalarizeMaskedMemIntrin/AArch64/streaming-compatible-expand-masked-gather-scatter.ll
@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -enable-new-pm=0 -S %s -scalarize-masked-mem-intrin -mtriple=aarch64-linux-gnu -mattr=+sve -force-streaming-compatible-sve | FileCheck %s
+
+define <2 x i32> @scalarize_v2i32(<2 x ptr> %p, <2 x i1> %mask, <2 x i32> %passthru) {
+; CHECK-LABEL: @scalarize_v2i32(
+; CHECK-NEXT:    [[SCALAR_MASK:%.*]] = bitcast <2 x i1> [[MASK:%.*]] to i2
+; CHECK-NEXT:    [[TMP1:%.*]] = and i2 [[SCALAR_MASK]], 1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne i2 [[TMP1]], 0
+; CHECK-NEXT:    br i1 [[TMP2]], label [[COND_LOAD:%.*]], label [[ELSE:%.*]]
+; CHECK:       cond.load:
+; CHECK-NEXT:    [[PTR0:%.*]] = extractelement <2 x ptr> [[P:%.*]], i64 0
+; CHECK-NEXT:    [[LOAD0:%.*]] = load i32, ptr [[PTR0]], align 8
+; CHECK-NEXT:    [[RES0:%.*]] = insertelement <2 x i32> [[PASSTHRU:%.*]], i32 [[LOAD0]], i64 0
+; CHECK-NEXT:    br label [[ELSE]]
+; CHECK:       else:
+; CHECK-NEXT:    [[RES_PHI_ELSE:%.*]] = phi <2 x i32> [ [[RES0]], [[COND_LOAD]] ], [ [[PASSTHRU]], [[TMP0:%.*]] ]
+; CHECK-NEXT:    [[TMP3:%.*]] = and i2 [[SCALAR_MASK]], -2
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp ne i2 [[TMP3]], 0
+; CHECK-NEXT:    br i1 [[TMP4]], label [[COND_LOAD1:%.*]], label [[ELSE2:%.*]]
+; CHECK:       cond.load1:
+; CHECK-NEXT:    [[PTR1:%.*]] = extractelement <2 x ptr> [[P]], i64 1
+; CHECK-NEXT:    [[LOAD1:%.*]] = load i32, ptr [[PTR1]], align 8
+; CHECK-NEXT:    [[RES1:%.*]] = insertelement <2 x i32> [[RES_PHI_ELSE]], i32 [[LOAD1]], i64 1
+; CHECK-NEXT:    br label [[ELSE2]]
+; CHECK:       else2:
+; CHECK-NEXT:    [[RES_PHI_ELSE3:%.*]] = phi <2 x i32> [ [[RES1]], [[COND_LOAD1]] ], [ [[RES_PHI_ELSE]], [[ELSE]] ]
+; CHECK-NEXT:    ret <2 x i32> [[RES_PHI_ELSE3]]
+;
+  %ret = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x ptr> %p, i32 8, <2 x i1> %mask, <2 x i32> %passthru)
+  ret <2 x i32> %ret
+}
+
+define void @scalarize_v2i64(<2 x ptr> %p, <2 x i1> %mask, <2 x i64> %value) {
+; CHECK-LABEL: @scalarize_v2i64(
+; CHECK-NEXT:    [[SCALAR_MASK:%.*]] = bitcast <2 x i1> [[MASK:%.*]] to i2
+; CHECK-NEXT:    [[TMP1:%.*]] = and i2 [[SCALAR_MASK]], 1
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp ne i2 [[TMP1]], 0
+; CHECK-NEXT:    br i1 [[TMP2]], label [[COND_STORE:%.*]], label [[ELSE:%.*]]
+; CHECK:       cond.store:
+; CHECK-NEXT:    [[ELT0:%.*]] = extractelement <2 x i64> [[VALUE:%.*]], i64 0
+; CHECK-NEXT:    [[PTR0:%.*]] = extractelement <2 x ptr> [[P:%.*]], i64 0
+; CHECK-NEXT:    store i64 [[ELT0]], ptr [[PTR0]], align 8
+; CHECK-NEXT:    br label [[ELSE]]
+; CHECK:       else:
+; CHECK-NEXT:    [[TMP3:%.*]] = and i2 [[SCALAR_MASK]], -2
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp ne i2 [[TMP3]], 0
+; CHECK-NEXT:    br i1 [[TMP4]], label [[COND_STORE1:%.*]], label [[ELSE2:%.*]]
+; CHECK:       cond.store1:
+; CHECK-NEXT:    [[ELT1:%.*]] = extractelement <2 x i64> [[VALUE]], i64 1
+; CHECK-NEXT:    [[PTR1:%.*]] = extractelement <2 x ptr> [[P]], i64 1
+; CHECK-NEXT:    store i64 [[ELT1]], ptr [[PTR1]], align 8
+; CHECK-NEXT:    br label [[ELSE2]]
+; CHECK:       else2:
+; CHECK-NEXT:    ret void
+;
+  call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> %value, <2 x ptr> %p, i32 8, <2 x i1> %mask)
+  ret void
+}
+
+declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)
+declare void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64>, <2 x i64*>, i32, <2 x i1>)