[llvm][CodeGen] Do not scalarize `llvm.masked.[gather|scatter]` operating on scalable vectors.

This patch prevents the `llvm.masked.gather` and `llvm.masked.scatter` intrinsics to be scalarized when invoked on scalable vectors.

The change in `Function.cpp` is needed to prevent the warning that is raised when `getNumElements` is used in place of `getElementCount` on `VectorType` instances. The tests guards for regressions on this change.

The tests makes sure that calls to `llvm.masked.[gather|scatter]` are still scalarized when:

  # the intrinsics are operating on fixed size vectors, and
  # the compiler is not targeting fixed length SVE code generation.

Reviewed By: efriedma, sdesmalen

Differential Revision: https://reviews.llvm.org/D86249

llvm/lib/CodeGen/ScalarizeMaskedMemIntrin.cpp

@@ -865,6 +865,12 @@ bool ScalarizeMaskedMemIntrin::optimizeCallInst(CallInst *CI,
                                                 bool &ModifiedDT) {
   IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
   if (II) {
+    // The scalarization code below does not work for scalable vectors.
+    if (isa<ScalableVectorType>(II->getType()) ||
+        any_of(II->arg_operands(),
+               [](Value *V) { return isa<ScalableVectorType>(V->getType()); }))
+      return false;
+
     switch (II->getIntrinsicID()) {
     default:
       break;

llvm/lib/IR/Function.cpp

@@ -1400,8 +1400,7 @@ static bool matchIntrinsicType(
       auto *ReferenceType = dyn_cast<VectorType>(ArgTys[RefArgNumber]);
       auto *ThisArgVecTy = dyn_cast<VectorType>(Ty);
       if (!ThisArgVecTy || !ReferenceType ||
-          (cast<FixedVectorType>(ReferenceType)->getNumElements() !=
-           cast<FixedVectorType>(ThisArgVecTy)->getNumElements()))
+          (ReferenceType->getElementCount() != ThisArgVecTy->getElementCount()))
         return true;
       PointerType *ThisArgEltTy =
           dyn_cast<PointerType>(ThisArgVecTy->getElementType());

llvm/test/CodeGen/AArch64/llvm-masked-gather-legal-for-sve.ll

@@ -0,0 +1,63 @@
+; RUN: opt -mtriple=aarch64-linux-gnu -mattr=+sve -scalarize-masked-mem-intrin -S < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+; Testing that masked gathers operating on scalable vectors that are
+; packed in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_gather_nxv4i32(
+; CHECK: call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32
+define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x i32*> %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru) {
+  %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+  ret <vscale x 4 x i32> %res
+}
+
+; Testing that masked gathers operating on scalable vectors of FP data
+; that is packed in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_gather_nxv2f64(
+; CHECK: call <vscale x 2 x double> @llvm.masked.gather.nxv2f64
+define <vscale x 2 x double> @masked_gather_nxv2f64(<vscale x 2 x double*> %ld, <vscale x 2 x i1> %masks, <vscale x 2 x double> %passthru) {
+  %res = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x double*> %ld, i32 0, <vscale x 2 x i1> %masks, <vscale x 2 x double> %passthru)
+  ret <vscale x 2 x double> %res
+}
+
+; Testing that masked gathers operating on scalable vectors of FP data
+; that is unpacked in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_gather_nxv2f16(
+; CHECK: call <vscale x 2 x half> @llvm.masked.gather.nxv2f16
+define <vscale x 2 x half> @masked_gather_nxv2f16(<vscale x 2 x half*> %ld, <vscale x 2 x i1> %masks, <vscale x 2 x half> %passthru) {
+  %res = call <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x half*> %ld, i32 0, <vscale x 2 x i1> %masks, <vscale x 2 x half> %passthru)
+  ret <vscale x 2 x half> %res
+}
+
+; Testing that masked gathers operating on 64-bit fixed vectors are
+; scalarized because NEON doesn't have support for masked gather
+; instructions.
+
+; CHECK-LABEL: @masked_gather_v2f32(
+; CHECK-NOT: @llvm.masked.gather.v2f32(
+define <2 x float> @masked_gather_v2f32(<2 x float*> %ld, <2 x i1> %masks, <2 x float> %passthru) {
+  %res = call <2 x float> @llvm.masked.gather.v2f32(<2 x float*> %ld, i32 0, <2 x i1> %masks, <2 x float> %passthru)
+  ret <2 x float> %res
+}
+
+; Testing that masked gathers operating on 128-bit fixed vectors are
+; scalarized because NEON doesn't have support for masked gather
+; instructions and because we are not targeting fixed width SVE.
+
+; CHECK-LABEL: @masked_gather_v4i32(
+; CHECK-NOT: @llvm.masked.gather.v4i32(
+define <4 x i32> @masked_gather_v4i32(<4 x i32*> %ld, <4 x i1> %masks, <4 x i32> %passthru) {
+  %res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
+  ret <4 x i32> %res
+}
+
+declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
+declare <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x double*> %ptrs, i32 %align, <vscale x 2 x i1> %masks, <vscale x 2 x double> %passthru)
+declare <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x half*> %ptrs, i32 %align, <vscale x 2 x i1> %masks, <vscale x 2 x half> %passthru)
+declare <2 x float> @llvm.masked.gather.v2f32(<2 x float*> %ptrs, i32 %align, <2 x i1> %masks, <2 x float> %passthru)
+declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 %align, <4 x i1> %masks, <4 x i32> %passthru)

llvm/test/CodeGen/AArch64/llvm-masked-scatter-legal-for-sve.ll

@@ -0,0 +1,63 @@
+; RUN: opt -mtriple=aarch64-linux-gnu -mattr=+sve -scalarize-masked-mem-intrin -S < %s 2>%t | FileCheck %s
+; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t
+
+; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it.
+; WARN-NOT: warning
+
+; Testing that masked scatters operating on scalable vectors that are
+; packed in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_scatter_nxv4i32(
+; CHECK: call void @llvm.masked.scatter.nxv4i32
+define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, <vscale x 4 x i1> %masks) {
+  call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 0, <vscale x 4 x i1> %masks)
+  ret void
+}
+
+; Testing that masked scatters operating on scalable vectors of FP
+; data that is packed in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_scatter_nxv2f64(
+; CHECK: call void @llvm.masked.scatter.nxv2f64
+define void @masked_scatter_nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, <vscale x 2 x i1> %masks) {
+  call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
+  ret void
+}
+
+; Testing that masked scatters operating on scalable vectors of FP
+; data that is unpacked in SVE registers are not scalarized.
+
+; CHECK-LABEL: @masked_scatter_nxv2f16(
+; CHECK: call void @llvm.masked.scatter.nxv2f16
+define void @masked_scatter_nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, <vscale x 2 x i1> %masks) {
+  call void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
+  ret void
+}
+
+; Testing that masked scatters operating on 64-bit fixed vectors are
+; scalarized because NEON doesn't have support for masked scatter
+; instructions.
+
+; CHECK-LABEL: @masked_scatter_v2f32(
+; CHECK-NOT: @llvm.masked.scatter.v2f32(
+define void @masked_scatter_v2f32(<2 x float> %data, <2 x float*> %ptrs, <2 x i1> %masks) {
+  call void @llvm.masked.scatter.v2f32(<2 x float> %data, <2 x float*> %ptrs, i32 0, <2 x i1> %masks)
+  ret void
+}
+
+; Testing that masked scatters operating on 128-bit fixed vectors are
+; scalarized because NEON doesn't have support for masked scatter
+; instructions and because we are not targeting fixed width SVE.
+
+; CHECK-LABEL: @masked_scatter_v4i32(
+; CHECK-NOT: @llvm.masked.scatter.v4i32(
+define void @masked_scatter_v4i32(<4 x i32> %data, <4 x i32*> %ptrs, <4 x i1> %masks) {
+  call void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 0, <4 x i1> %masks)
+  ret void
+}
+
+declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x i32*> %ptrs, i32 %align, <vscale x 4 x i1> %masks)
+declare void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, i32 %align, <vscale x 2 x i1> %masks)
+declare void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, i32 %align, <vscale x 2 x i1> %masks)
+declare void @llvm.masked.scatter.v2f32(<2 x float> %data, <2 x float*> %ptrs, i32 %align, <2 x i1> %masks)
+declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x i32*> %ptrs, i32 %align, <4 x i1> %masks)