This reverts commit b0b3e3e1c7f6387eabc2ef9ff1fea311e63a4299. After thinking about this for a bit, I don't think this is correct. vscale being a power-of-2 only guarantees the canonical IV increment overflows to zero, but not overflows in general.
60 lines
3.7 KiB
LLVM
60 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 6
|
|
; RUN: opt < %s -S -p loop-vectorize -force-vector-width=4 -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue | FileCheck %s
|
|
|
|
define i32 @f(ptr noalias %p, i32 %start, i32 %step, i32 %n) {
|
|
; CHECK-LABEL: define i32 @f(
|
|
; CHECK-SAME: ptr noalias [[P:%.*]], i32 [[START:%.*]], i32 [[STEP:%.*]], i32 [[N:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[N]], 1
|
|
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[TMP0]], 3
|
|
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], 4
|
|
; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
|
|
; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[TMP0]], 1
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT3:%.*]] = insertelement <4 x i32> poison, i32 [[STEP]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT4:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT3]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[TMP1:%.*]] = mul <4 x i32> <i32 0, i32 1, i32 2, i32 3>, [[BROADCAST_SPLAT4]]
|
|
; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT2]], [[TMP1]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = shl i32 [[STEP]], 2
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT5:%.*]] = insertelement <4 x i32> poison, i32 [[TMP2]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT6:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT5]], <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: [[VEC_IND:%.*]] = phi <4 x i32> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
|
|
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT6]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
|
|
; CHECK-NEXT: br i1 [[TMP3]], label %[[SCALAR_PH:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: [[SCALAR_PH]]:
|
|
; CHECK-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <4 x i32> poison, i32 [[INDEX]], i64 0
|
|
; CHECK-NEXT: [[BROADCAST_SPLAT8:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT7]], <4 x i32> poison, <4 x i32> zeroinitializer
|
|
; CHECK-NEXT: [[VEC_IV:%.*]] = add <4 x i32> [[BROADCAST_SPLAT8]], <i32 0, i32 1, i32 2, i32 3>
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp ugt <4 x i32> [[VEC_IV]], [[BROADCAST_SPLAT]]
|
|
; CHECK-NEXT: [[FIRST_INACTIVE_LANE:%.*]] = call i64 @llvm.experimental.cttz.elts.i64.v4i1(<4 x i1> [[TMP4]], i1 false)
|
|
; CHECK-NEXT: [[LAST_ACTIVE_LANE:%.*]] = sub i64 [[FIRST_INACTIVE_LANE]], 1
|
|
; CHECK-NEXT: [[IV2_LCSSA:%.*]] = extractelement <4 x i32> [[VEC_IND]], i64 [[LAST_ACTIVE_LANE]]
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: ret i32 [[IV2_LCSSA]]
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i32 [0, %entry], [%iv.next, %loop]
|
|
%iv2 = phi i32 [%start, %entry], [%iv2.next, %loop]
|
|
%iv.next = add i32 %iv, 1
|
|
%iv2.next = add i32 %iv2, %step
|
|
%ec = icmp eq i32 %iv, %n
|
|
br i1 %ec, label %exit, label %loop
|
|
|
|
exit:
|
|
ret i32 %iv2
|
|
}
|