[llvm] [LV] Regenerate literal struct return tests with UTC. NFC (PR #160268)
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Tue Sep 23 03:18:45 PDT 2025
================
@@ -1,18 +1,63 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
; RUN: opt < %s -mattr=+sve -passes=loop-vectorize -force-vector-interleave=1 -prefer-predicate-over-epilogue=predicate-dont-vectorize -S | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; Tests basic vectorization of scalable homogeneous struct literal returns.
define void @struct_return_f32_widen(ptr noalias %in, ptr noalias writeonly %out_a, ptr noalias writeonly %out_b) {
-; CHECK-LABEL: define void @struct_return_f32_widen
-; CHECK-SAME: (ptr noalias [[IN:%.*]], ptr noalias writeonly [[OUT_A:%.*]], ptr noalias writeonly [[OUT_B:%.*]])
-; CHECK: vector.body:
-; CHECK: [[WIDE_CALL:%.*]] = call { <vscale x 4 x float>, <vscale x 4 x float> } @scalable_vec_masked_foo(<vscale x 4 x float> [[WIDE_MASKED_LOAD:%.*]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK:%.*]])
-; CHECK: [[WIDE_A:%.*]] = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } [[WIDE_CALL]], 0
-; CHECK: [[WIDE_B:%.*]] = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } [[WIDE_CALL]], 1
-; CHECK: call void @llvm.masked.store.nxv4f32.p0(<vscale x 4 x float> [[WIDE_A]], ptr {{%.*}}, i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
-; CHECK: call void @llvm.masked.store.nxv4f32.p0(<vscale x 4 x float> [[WIDE_B]], ptr {{%.*}}, i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-LABEL: define void @struct_return_f32_widen(
+; CHECK-SAME: ptr noalias [[IN:%.*]], ptr noalias writeonly [[OUT_A:%.*]], ptr noalias writeonly [[OUT_B:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = mul nuw i64 [[TMP0]], 4
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 2
+; CHECK-NEXT: [[TMP4:%.*]] = sub i64 1024, [[TMP3]]
+; CHECK-NEXT: [[TMP5:%.*]] = icmp ugt i64 1024, [[TMP3]]
+; CHECK-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], i64 [[TMP4]], i64 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 1024)
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], %[[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, ptr [[IN]], i64 [[INDEX]]
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0(ptr [[TMP7]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
+; CHECK-NEXT: [[TMP8:%.*]] = call { <vscale x 4 x float>, <vscale x 4 x float> } @scalable_vec_masked_foo(<vscale x 4 x float> [[WIDE_MASKED_LOAD]], <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[TMP9:%.*]] = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP8]], 0
+; CHECK-NEXT: [[TMP10:%.*]] = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } [[TMP8]], 1
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds float, ptr [[OUT_A]], i64 [[INDEX]]
+; CHECK-NEXT: call void @llvm.masked.store.nxv4f32.p0(<vscale x 4 x float> [[TMP9]], ptr [[TMP11]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds float, ptr [[OUT_B]], i64 [[INDEX]]
+; CHECK-NEXT: call void @llvm.masked.store.nxv4f32.p0(<vscale x 4 x float> [[TMP10]], ptr [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP1]]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX]], i64 [[TMP6]])
+; CHECK-NEXT: [[TMP13:%.*]] = extractelement <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], i32 0
+; CHECK-NEXT: [[TMP14:%.*]] = xor i1 [[TMP13]], true
+; CHECK-NEXT: br i1 [[TMP14]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br label %[[EXIT:.*]]
+; CHECK: [[SCALAR_PH:.*]]:
----------------
fhahn wrote:
I think you can filter out anything after scalar.ph
https://github.com/llvm/llvm-project/pull/160268
More information about the llvm-commits
mailing list