[llvm] [LV] Vectorize FMax w/o fast-math flags. (PR #146711)

[Florian Hahn via llvm-commits]

================
@@ -317,10 +449,58 @@ define float @fmax_with_select_and_load_store(ptr %src, ptr noalias %dst, i64 %n
 ; CHECK-LABEL: define float @fmax_with_select_and_load_store(
 ; CHECK-SAME: ptr [[SRC:%.*]], ptr noalias [[DST:%.*]], i64 [[N:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 4
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], 4
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[IV1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i64> [ splat (i64 -1), %[[VECTOR_PH]] ], [ [[TMP9:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI1:%.*]] = phi <4 x float> [ splat (float -1.000000e+07), %[[VECTOR_PH]] ], [ [[TMP8:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[GEP_SRC1:%.*]] = getelementptr inbounds nuw float, ptr [[SRC]], i64 [[IV1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds nuw float, ptr [[GEP_SRC1]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = fcmp ugt <4 x float> [[WIDE_LOAD]], [[VEC_PHI1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IV1]], 1
+; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[TMP4]], i32 0
+; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <4 x i32>, ptr [[TMP5]], align 4
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[DST]], i64 [[IV1]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP6]], i32 0
+; CHECK-NEXT:    store <4 x i32> [[WIDE_LOAD2]], ptr [[TMP7]], align 4
+; CHECK-NEXT:    [[TMP8]] = select <4 x i1> [[TMP2]], <4 x float> [[WIDE_LOAD]], <4 x float> [[VEC_PHI1]]
+; CHECK-NEXT:    [[TMP9]] = select <4 x i1> [[TMP2]], <4 x i64> [[VEC_IND]], <4 x i64> [[VEC_PHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[IV1]], 4
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
+; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP10]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP11:%.*]] = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> [[TMP8]])
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[TMP11]], i64 0
+; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP12:%.*]] = fcmp oeq <4 x float> [[TMP8]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT:    [[TMP13:%.*]] = select <4 x i1> [[TMP12]], <4 x i64> [[TMP9]], <4 x i64> splat (i64 -1)
+; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vector.reduce.umin.v4i64(<4 x i64> [[TMP13]])
+; CHECK-NEXT:    [[RDX_SELECT_CMP:%.*]] = icmp ne i64 [[TMP14]], -1
+; CHECK-NEXT:    [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP]], i64 [[TMP14]], i64 0
----------------
fhahn wrote:

Yep, in that case, the maximum has never been updated in the loop, selecting the first lane, which contains the initial value.

https://github.com/llvm/llvm-project/pull/146711