[SVE] Add test to show incorrect code generation for scalable vector struct loads...

Patch also includes a minor fix to AArch64::isLegalAddressingMode
to ensure all scalable types have a suitable bailout.

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index c8a461a924b48551fda0eaa0f7ac1a8561b09319..0605dfa6379399cbad1180d5e1cb295c8b840005 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -15480,15 +15480,15 @@ bool AArch64TargetLowering::isLegalAddressingMode(const DataLayout &DL,
   if (!AM.HasBaseReg)
     return false;
 
-  // FIXME: Update this method to support scalable addressing modes.
-  if (Ty->isScalableTargetExtTy())
-    return AM.HasBaseReg && !AM.BaseOffs && !AM.Scale;
+  if (Ty->isScalableTy()) {
+    if (isa<ScalableVectorType>(Ty)) {
+      uint64_t VecElemNumBytes =
+          DL.getTypeSizeInBits(cast<VectorType>(Ty)->getElementType()) / 8;
+      return AM.HasBaseReg && !AM.BaseOffs &&
+             (AM.Scale == 0 || (uint64_t)AM.Scale == VecElemNumBytes);
+    }
 
-  if (isa<ScalableVectorType>(Ty)) {
-    uint64_t VecElemNumBytes =
-        DL.getTypeSizeInBits(cast<VectorType>(Ty)->getElementType()) / 8;
-    return AM.HasBaseReg && !AM.BaseOffs &&
-           (AM.Scale == 0 || (uint64_t)AM.Scale == VecElemNumBytes);
+    return AM.HasBaseReg && !AM.BaseOffs && !AM.Scale;
   }
 
   // check reg + imm case:

diff --git a/llvm/test/CodeGen/AArch64/alloca-load-store-scalable-struct.ll b/llvm/test/CodeGen/AArch64/alloca-load-store-scalable-struct.ll
new file mode 100644 (file)
index 0000000..0984b6b
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/alloca-load-store-scalable-struct.ll
@@ -0,0 +1,35 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc < %s | FileCheck %s
+
+target triple = "aarch64-unknown-linux-gnu"
+
+%struct.test = type { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> }
+
+define void @test(ptr %addr) #0 {
+; CHECK-LABEL: test:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str x29, [sp, #-16]! // 8-byte Folded Spill
+; CHECK-NEXT:    addvl sp, sp, #-3
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
+; CHECK-NEXT:    .cfi_offset w29, -16
+; CHECK-NEXT:    mov x8, #2 // =0x2
+; CHECK-NEXT:    mov x9, #4 // =0x4
+; CHECK-NEXT:    ptrue p0.d
+; CHECK-NEXT:    mov x10, sp
+; CHECK-NEXT:    ld1d { z0.d }, p0/z, [x0, x8, lsl #3]
+; CHECK-NEXT:    ld1d { z1.d }, p0/z, [x0, x9, lsl #3]
+; CHECK-NEXT:    ld1d { z2.d }, p0/z, [x0]
+; CHECK-NEXT:    st1d { z0.d }, p0, [x10, x8, lsl #3]
+; CHECK-NEXT:    st1d { z1.d }, p0, [x10, x9, lsl #3]
+; CHECK-NEXT:    st1d { z2.d }, p0, [sp]
+; CHECK-NEXT:    addvl sp, sp, #3
+; CHECK-NEXT:    ldr x29, [sp], #16 // 8-byte Folded Reload
+; CHECK-NEXT:    ret
+entry:
+  %ret = alloca %struct.test, align 8
+  %val = load %struct.test, ptr %addr
+  store %struct.test %val, ptr %ret, align 8
+  ret void
+}
+
+attributes #0 = { "target-features"="+sve" }