[LV] Add partial reduction tests multiplying extend with constants.

1 files changed, 469 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
new file mode 100644
index 0000000..0086f6e
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-constant-ops.ll
@@ -0,0 +1,469 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
+; RUN: opt --mattr=+neon,+dotprod -passes=loop-vectorize -force-vector-interleave=1 -enable-epilogue-vectorization=false -S %s | FileCheck %s
+
+target triple = "arm64-apple-macosx"
+
+define i32 @red_zext_mul_by_63(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_zext_mul_by_63(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = zext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 63)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = zext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 63
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr.iv = phi ptr [ %start, %entry ], [ %gep.iv.next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
+  %l = load i8, ptr %ptr.iv, align 1
+  %l.ext = zext i8 %l to i32
+  %mul = mul i32 %l.ext, 63
+  %red.next = add i32 %red, %mul
+  %gep.iv.next = getelementptr i8, ptr %ptr.iv, i64 1
+  %ec = icmp eq ptr %ptr.iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret i32 %red.next
+}
+
+define i32 @red_zext_mul_by_255(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_zext_mul_by_255(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = zext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 255)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = zext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 255
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr.iv = phi ptr [ %start, %entry ], [ %gep.iv.next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
+  %l = load i8, ptr %ptr.iv, align 1
+  %l.ext = zext i8 %l to i32
+  %mul = mul i32 %l.ext, 255
+  %red.next = add i32 %red, %mul
+  %gep.iv.next = getelementptr i8, ptr %ptr.iv, i64 1
+  %ec = icmp eq ptr %ptr.iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret i32 %red.next
+}
+
+define i32 @red_zext_mul_by_256(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_zext_mul_by_256(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = zext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 256)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = zext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 256
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr.iv = phi ptr [ %start, %entry ], [ %gep.iv.next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
+  %l = load i8, ptr %ptr.iv, align 1
+  %l.ext = zext i8 %l to i32
+  %mul = mul i32 %l.ext, 256
+  %red.next = add i32 %red, %mul
+  %gep.iv.next = getelementptr i8, ptr %ptr.iv, i64 1
+  %ec = icmp eq ptr %ptr.iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret i32 %red.next
+}
+
+define i32 @red_sext_mul_by_63(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_sext_mul_by_63(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 63)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = sext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 63
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr_iv = phi ptr [ %start, %entry ], [ %gep_iv_next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red_next, %loop ]
+  %l = load i8, ptr %ptr_iv, align 1
+  %l_ext = sext i8 %l to i32
+  %mul = mul i32 %l_ext, 63
+  %red_next = add i32 %red, %mul
+  %gep_iv_next = getelementptr i8, ptr %ptr_iv, i64 1
+  %ec = icmp eq ptr %ptr_iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  %red_next_lcssa = phi i32 [ %red_next, %loop ]
+  ret i32 %red_next_lcssa
+}
+
+; Constants >= 128 cannot be treated as sign-extended.
+define i32 @red_sext_mul_by_128(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_sext_mul_by_128(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 128)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = sext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 128
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr_iv = phi ptr [ %start, %entry ], [ %gep_iv_next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red_next, %loop ]
+  %l = load i8, ptr %ptr_iv, align 1
+  %l_ext = sext i8 %l to i32
+  %mul = mul i32 %l_ext, 128
+  %red_next = add i32 %red, %mul
+  %gep_iv_next = getelementptr i8, ptr %ptr_iv, i64 1
+  %ec = icmp eq ptr %ptr_iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  %red_next_lcssa = phi i32 [ %red_next, %loop ]
+  ret i32 %red_next_lcssa
+}
+
+define i32 @red_sext_mul_by_255(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_sext_mul_by_255(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 255)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = sext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 255
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr.iv = phi ptr [ %start, %entry ], [ %gep.iv.next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
+  %l = load i8, ptr %ptr.iv, align 1
+  %l.ext = sext i8 %l to i32
+  %mul = mul i32 %l.ext, 255
+  %red.next = add i32 %red, %mul
+  %gep.iv.next = getelementptr i8, ptr %ptr.iv, i64 1
+  %ec = icmp eq ptr %ptr.iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret i32 %red.next
+}
+
+define i32 @red_sext_mul_by_256(ptr %start, ptr %end) {
+; CHECK-LABEL: define i32 @red_sext_mul_by_256(
+; CHECK-SAME: ptr [[START:%.*]], ptr [[END:%.*]]) #[[ATTR0]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[START2:%.*]] = ptrtoint ptr [[START]] to i64
+; CHECK-NEXT:    [[END1:%.*]] = ptrtoint ptr [[END]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[END1]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = sub i64 [[TMP0]], [[START2]]
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 16
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK:       [[VECTOR_PH]]:
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP1]], 16
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP1]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i8, ptr [[START]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
+; CHECK:       [[VECTOR_BODY]]:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <16 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[START]], i64 [[INDEX]]
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[NEXT_GEP]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = sext <16 x i8> [[WIDE_LOAD]] to <16 x i32>
+; CHECK-NEXT:    [[TMP4:%.*]] = mul <16 x i32> [[TMP3]], splat (i32 256)
+; CHECK-NEXT:    [[TMP5]] = add <16 x i32> [[VEC_PHI]], [[TMP4]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK:       [[MIDDLE_BLOCK]]:
+; CHECK-NEXT:    [[TMP7:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP5]])
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP1]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK:       [[SCALAR_PH]]:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi ptr [ [[TMP2]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
+; CHECK-NEXT:    [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP7]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[PTR_IV:%.*]] = phi ptr [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[GEP_IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[PTR_IV]], align 1
+; CHECK-NEXT:    [[L_EXT:%.*]] = sext i8 [[L]] to i32
+; CHECK-NEXT:    [[MUL:%.*]] = mul i32 [[L_EXT]], 256
+; CHECK-NEXT:    [[RED_NEXT]] = add i32 [[RED]], [[MUL]]
+; CHECK-NEXT:    [[GEP_IV_NEXT]] = getelementptr i8, ptr [[PTR_IV]], i64 1
+; CHECK-NEXT:    [[EC:%.*]] = icmp eq ptr [[PTR_IV]], [[END]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[TMP7]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT:    ret i32 [[RED_NEXT_LCSSA]]
+;
+entry:
+  br label %loop
+
+loop:
+  %ptr.iv = phi ptr [ %start, %entry ], [ %gep.iv.next, %loop ]
+  %red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
+  %l = load i8, ptr %ptr.iv, align 1
+  %l.ext = sext i8 %l to i32
+  %mul = mul i32 %l.ext, 256
+  %red.next = add i32 %red, %mul
+  %gep.iv.next = getelementptr i8, ptr %ptr.iv, i64 1
+  %ec = icmp eq ptr %ptr.iv, %end
+  br i1 %ec, label %exit, label %loop
+
+exit:
+  ret i32 %red.next
+}