3 files changed, 58 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AArch64/aarch64-sve-asm-negative.ll b/llvm/test/CodeGen/AArch64/aarch64-sve-asm-negative.ll
new file mode 100644
index 00000000000..ad483f40efb
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/aarch64-sve-asm-negative.ll
@@ -0,0 +1,12 @@
+; RUN: not llc -mtriple aarch64-none-linux-gnu -mattr=+neon -o %t.s -filetype=asm %s 2>&1 | FileCheck %s
+
+; The 'y' constraint only applies to SVE vector registers (Z0-Z7)
+; The test below ensures that we get an appropriate error should the
+; constraint be used with a Neon register.
+
+; Function Attrs: nounwind readnone
+; CHECK: error: couldn't allocate input reg for constraint 'y'
+define <4 x i32> @test_neon(<4 x i32> %in1, <4 x i32> %in2) {
+  %1 = tail call <4 x i32> asm "add $0.4s, $1.4s, $2.4s", "=w,w,y"(<4 x i32> %in1, <4 x i32> %in2)
+  ret <4 x i32> %1
+}
diff --git a/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll b/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll
new file mode 100644
index 00000000000..2ebb0830810
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/aarch64-sve-asm.ll
@@ -0,0 +1,44 @@
+; RUN: llc < %s -mtriple aarch64-none-linux-gnu -mattr=+sve -stop-after=finalize-isel | FileCheck %s --check-prefix=CHECK
+
+target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-none-linux-gnu"
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z1
+; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
+; CHECK: [[ARG4:%[0-9]+]]:zpr_3b = COPY [[ARG1]]
+define <vscale x 16 x i8> @test_svadd_i8(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm) {
+  %1 = tail call <vscale x 16 x i8> asm "add $0.b, $1.b, $2.b", "=w,w,y"(<vscale x 16 x i8> %Zn, <vscale x 16 x i8> %Zm)
+  ret <vscale x 16 x i8> %1
+}
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z1
+; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
+; CHECK: [[ARG4:%[0-9]+]]:zpr_4b = COPY [[ARG1]]
+define <vscale x 2 x i64> @test_svsub_i64(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm) {
+  %1 = tail call <vscale x 2 x i64> asm "sub $0.d, $1.d, $2.d", "=w,w,x"(<vscale x 2 x i64> %Zn, <vscale x 2 x i64> %Zm)
+  ret <vscale x 2 x i64> %1
+}
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z1
+; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
+; CHECK: [[ARG4:%[0-9]+]]:zpr_3b = COPY [[ARG1]]
+define <vscale x 8 x half> @test_svfmul_f16(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm) {
+  %1 = tail call <vscale x 8 x half> asm "fmul $0.h, $1.h, $2.h", "=w,w,y"(<vscale x 8 x half> %Zn, <vscale x 8 x half> %Zm)
+  ret <vscale x 8 x half> %1
+}
+
+; Function Attrs: nounwind readnone
+; CHECK: [[ARG1:%[0-9]+]]:zpr = COPY $z1
+; CHECK: [[ARG2:%[0-9]+]]:zpr = COPY $z0
+; CHECK: [[ARG3:%[0-9]+]]:zpr = COPY [[ARG2]]
+; CHECK: [[ARG4:%[0-9]+]]:zpr_4b = COPY [[ARG1]]
+define <vscale x 4 x float> @test_svfmul_f(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm) {
+  %1 = tail call <vscale x 4 x float> asm "fmul $0.s, $1.s, $2.s", "=w,w,x"(<vscale x 4 x float> %Zn, <vscale x 4 x float> %Zm)
+  ret <vscale x 4 x float> %1
+}
diff --git a/llvm/test/CodeGen/AArch64/arm64-inline-asm.ll b/llvm/test/CodeGen/AArch64/arm64-inline-asm.ll
index 82e0a1c3748..3b8b4d84873 100644
--- a/llvm/test/CodeGen/AArch64/arm64-inline-asm.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-inline-asm.ll
@@ -138,6 +138,8 @@ entry:
   %a = alloca [2 x float], align 4
   %arraydecay = getelementptr inbounds [2 x float], [2 x float]* %a, i32 0, i32 0
   %0 = load <2 x float>, <2 x float>* %data, align 8
+  call void asm sideeffect "ldr ${1:z}, [$0]\0A", "r,w"(float* %arraydecay, <2 x float> %0) nounwind
+  ; CHECK: ldr {{z[0-9]+}}, [{{x[0-9]+}}]
   call void asm sideeffect "ldr ${1:q}, [$0]\0A", "r,w"(float* %arraydecay, <2 x float> %0) nounwind
   ; CHECK: ldr {{q[0-9]+}}, [{{x[0-9]+}}]
   call void asm sideeffect "ldr ${1:d}, [$0]\0A", "r,w"(float* %arraydecay, <2 x float> %0) nounwind