Precommit test

Author: lukel97

llvm/test/Transforms/LoopVectorize/widen-intrinsic.ll

@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
+; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -S | FileCheck %s
+
+; Check that we don't unnecessarily broadcast %pow
+define void @powi(ptr noalias %p, i32 %pow) {
+; CHECK-LABEL: define void @powi(
+; CHECK-SAME: ptr noalias [[P:%.*]], i32 [[POW:%.*]]) {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[POW]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr float, ptr [[P]], i32 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr float, ptr [[TMP0]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[BROADCAST_SPLAT]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> [[WIDE_LOAD]], i32 [[TMP2]])
+; CHECK-NEXT:    store <4 x float> [[TMP3]], ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
+; CHECK-NEXT:    br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 1024, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[P_GEP:%.*]] = getelementptr float, ptr [[P]], i32 [[IV]]
+; CHECK-NEXT:    [[X:%.*]] = load float, ptr [[P_GEP]], align 4
+; CHECK-NEXT:    [[Y:%.*]] = call float @llvm.powi.f32.i32(float [[X]], i32 [[POW]])
+; CHECK-NEXT:    store float [[Y]], ptr [[P_GEP]], align 4
+; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i32 [[IV_NEXT]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [0, %entry], [%iv.next, %loop]
+  %p.gep = getelementptr float, ptr %p, i32 %iv
+  %x = load float, ptr %p.gep
+  %y = call float @llvm.powi(float %x, i32 %pow)
+  store float %y, ptr %p.gep
+  %iv.next = add i32 %iv, 1
+  %done = icmp eq i32 %iv.next, 1024
+  br i1 %done, label %exit, label %loop
+
+exit:
+  ret void
+}