[llvm] 377dcfd - [Tests] Auto update a vectorizer test to simplify future diff
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Sun Jan 10 12:23:40 PST 2021
Author: Philip Reames
Date: 2021-01-10T12:23:22-08:00
New Revision: 377dcfd5c15d8e2c9e71a171635529052a96e244
URL: https://github.com/llvm/llvm-project/commit/377dcfd5c15d8e2c9e71a171635529052a96e244
DIFF: https://github.com/llvm/llvm-project/commit/377dcfd5c15d8e2c9e71a171635529052a96e244.diff
LOG: [Tests] Auto update a vectorizer test to simplify future diff
Added:
Modified:
llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
Removed:
################################################################################
diff --git a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
index a3cdf7bf3e40..208e1a219be8 100644
--- a/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
+++ b/llvm/test/Transforms/LoopVectorize/first-order-recurrence-complex.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
@@ -7,32 +8,62 @@
; Test case for PR43398.
define void @can_sink_after_store(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
-; CHECK-LABEL: vector.ph:
-; CHECK: %broadcast.splatinsert = insertelement <4 x i32> poison, i32 %x, i32 0
-; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> poison, i32 %.pre, i32 3
-; CHECK-NEXT: br label %vector.body
-
-; CHECK-LABEL: vector.body:
-; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
-; CHECK-NEXT: %offset.idx = add i64 1, %index
-; CHECK-NEXT: %0 = add i64 %offset.idx, 0
-; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
-; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
-; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
-; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
-; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
-; CHECK-NEXT: %5 = add <4 x i32> %4, %broadcast.splat
-; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
-; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
-; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0
-; CHECK-NEXT: %9 = bitcast i32* %8 to <4 x i32>*
-; CHECK-NEXT: store <4 x i32> %6, <4 x i32>* %9, align 4
-; CHECK-NEXT: %index.next = add i64 %index, 4
-; CHECK-NEXT: %10 = icmp eq i64 %index.next, 1996
-; CHECK-NEXT: br i1 %10, label %middle.block, label %vector.body
+; CHECK-LABEL: @can_sink_after_store(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[PREHEADER:%.*]]
+; CHECK: preheader:
+; CHECK-NEXT: [[IDX_PHI_TRANS:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
+; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* [[IDX_PHI_TRANS]], align 4
+; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[X:%.*]], i32 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[VECTOR_RECUR_INIT:%.*]] = insertelement <4 x i32> poison, i32 [[DOTPRE]], i32 3
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <4 x i32> [ [[VECTOR_RECUR_INIT]], [[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 1, [[INDEX]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
+; CHECK-NEXT: [[WIDE_LOAD]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[VECTOR_RECUR]], <4 x i32> [[WIDE_LOAD]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i32> [[TMP5]], [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[TMP0]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[TMP7]], i32 0
+; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>*
+; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP9]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1996
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
+; CHECK: middle.block:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 1999, 1996
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 2
+; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ [[DOTPRE]], [[PREHEADER]] ], [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 1997, [[MIDDLE_BLOCK]] ], [ 1, [[PREHEADER]] ]
+; CHECK-NEXT: br label [[FOR:%.*]]
+; CHECK: for:
+; CHECK-NEXT: [[SCALAR_RECUR:%.*]] = phi i32 [ [[SCALAR_RECUR_INIT]], [[SCALAR_PH]] ], [ [[PRE_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[ADD_1:%.*]] = add i32 [[SCALAR_RECUR]], [[X]]
+; CHECK-NEXT: [[IDX_1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[IV]]
+; CHECK-NEXT: [[PRE_NEXT]] = load i32, i32* [[IDX_1]], align 4
+; CHECK-NEXT: [[ADD_2:%.*]] = add i32 [[ADD_1]], [[PRE_NEXT]]
+; CHECK-NEXT: [[IDX_2:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[IV]]
+; CHECK-NEXT: store i32 [[ADD_2]], i32* [[IDX_2]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], [[LOOP2:!llvm.loop !.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
;
+
entry:
br label %preheader
@@ -61,32 +92,62 @@ exit:
; We can sink potential trapping instructions, as this will only delay the trap
; and not introduce traps on additional paths.
define void @sink_sdiv(i32 %x, i32* %ptr, i64 %tc) local_unnamed_addr #0 {
-; CHECK-LABEL: vector.ph:
-; CHECK: %broadcast.splatinsert = insertelement <4 x i32> poison, i32 %x, i32 0
-; CHECK-NEXT: %broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT: %vector.recur.init = insertelement <4 x i32> poison, i32 %.pre, i32 3
-; CHECK-NEXT: br label %vector.body
-
-; CHECK-LABEL: vector.body:
-; CHECK-NEXT: %index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
-; CHECK-NEXT: %vector.recur = phi <4 x i32> [ %vector.recur.init, %vector.ph ], [ %wide.load, %vector.body ]
-; CHECK-NEXT: %offset.idx = add i64 1, %index
-; CHECK-NEXT: %0 = add i64 %offset.idx, 0
-; CHECK-NEXT: %1 = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 %0
-; CHECK-NEXT: %2 = getelementptr inbounds i32, i32* %1, i32 0
-; CHECK-NEXT: %3 = bitcast i32* %2 to <4 x i32>*
-; CHECK-NEXT: %wide.load = load <4 x i32>, <4 x i32>* %3, align 4
-; CHECK-NEXT: %4 = shufflevector <4 x i32> %vector.recur, <4 x i32> %wide.load, <4 x i32> <i32 3, i32 4, i32 5, i32 6>
-; CHECK-NEXT: %5 = sdiv <4 x i32> %4, %broadcast.splat
-; CHECK-NEXT: %6 = add <4 x i32> %5, %wide.load
-; CHECK-NEXT: %7 = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 %0
-; CHECK-NEXT: %8 = getelementptr inbounds i32, i32* %7, i32 0
-; CHECK-NEXT: %9 = bitcast i32* %8 to <4 x i32>*
-; CHECK-NEXT: store <4 x i32> %6, <4 x i32>* %9, align 4
-; CHECK-NEXT: %index.next = add i64 %index, 4
-; CHECK-NEXT: %10 = icmp eq i64 %index.next, 1996
-; CHECK-NEXT: br i1 %10, label %middle.block, label %vector.body
+; CHECK-LABEL: @sink_sdiv(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[PREHEADER:%.*]]
+; CHECK: preheader:
+; CHECK-NEXT: [[IDX_PHI_TRANS:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
+; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* [[IDX_PHI_TRANS]], align 4
+; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK: vector.ph:
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[X:%.*]], i32 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[VECTOR_RECUR_INIT:%.*]] = insertelement <4 x i32> poison, i32 [[DOTPRE]], i32 3
+; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
+; CHECK: vector.body:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VECTOR_RECUR:%.*]] = phi <4 x i32> [ [[VECTOR_RECUR_INIT]], [[VECTOR_PH]] ], [ [[WIDE_LOAD:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = add i64 1, [[INDEX]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[OFFSET_IDX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
+; CHECK-NEXT: [[WIDE_LOAD]] = load <4 x i32>, <4 x i32>* [[TMP3]], align 4
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[VECTOR_RECUR]], <4 x i32> [[WIDE_LOAD]], <4 x i32> <i32 3, i32 4, i32 5, i32 6>
+; CHECK-NEXT: [[TMP5:%.*]] = sdiv <4 x i32> [[TMP4]], [[BROADCAST_SPLAT]]
+; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i32> [[TMP5]], [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[TMP0]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, i32* [[TMP7]], i32 0
+; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[TMP8]] to <4 x i32>*
+; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP9]], align 4
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
+; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1996
+; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP4:!llvm.loop !.*]]
+; CHECK: middle.block:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 1999, 1996
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 3
+; CHECK-NEXT: [[VECTOR_RECUR_EXTRACT_FOR_PHI:%.*]] = extractelement <4 x i32> [[WIDE_LOAD]], i32 2
+; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK: scalar.ph:
+; CHECK-NEXT: [[SCALAR_RECUR_INIT:%.*]] = phi i32 [ [[DOTPRE]], [[PREHEADER]] ], [ [[VECTOR_RECUR_EXTRACT]], [[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 1997, [[MIDDLE_BLOCK]] ], [ 1, [[PREHEADER]] ]
+; CHECK-NEXT: br label [[FOR:%.*]]
+; CHECK: for:
+; CHECK-NEXT: [[SCALAR_RECUR:%.*]] = phi i32 [ [[SCALAR_RECUR_INIT]], [[SCALAR_PH]] ], [ [[PRE_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[DIV_1:%.*]] = sdiv i32 [[SCALAR_RECUR]], [[X]]
+; CHECK-NEXT: [[IDX_1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[IV]]
+; CHECK-NEXT: [[PRE_NEXT]] = load i32, i32* [[IDX_1]], align 4
+; CHECK-NEXT: [[ADD_2:%.*]] = add i32 [[DIV_1]], [[PRE_NEXT]]
+; CHECK-NEXT: [[IDX_2:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[IV]]
+; CHECK-NEXT: store i32 [[ADD_2]], i32* [[IDX_2]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT]], label [[FOR]], [[LOOP5:!llvm.loop !.*]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
;
+
entry:
br label %preheader
@@ -115,18 +176,33 @@ exit:
; FIXME: Currently we can only sink a single instruction. For the example below,
; we also have to sink users.
define void @cannot_sink_with_additional_user(i32 %x, i32* %ptr, i64 %tc) {
-; CHECK-LABEL: define void @cannot_sink_with_additional_user(
-; CHECK-NEXT: entry:
-; CHECK-NEXT: br label %preheader
+; CHECK-LABEL: @cannot_sink_with_additional_user(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[PREHEADER:%.*]]
+; CHECK: preheader:
+; CHECK-NEXT: [[IDX_PHI_TRANS:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
+; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* [[IDX_PHI_TRANS]], align 4
+; CHECK-NEXT: br label [[FOR:%.*]]
+; CHECK: for:
+; CHECK-NEXT: [[PRE_PHI:%.*]] = phi i32 [ [[DOTPRE]], [[PREHEADER]] ], [ [[PRE_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 1, [[PREHEADER]] ], [ [[IV_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[ADD_1:%.*]] = add i32 [[PRE_PHI]], [[X:%.*]]
+; CHECK-NEXT: [[ADD_2:%.*]] = add i32 [[ADD_1]], [[X]]
+; CHECK-NEXT: [[IDX_1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[IV]]
+; CHECK-NEXT: [[PRE_NEXT]] = load i32, i32* [[IDX_1]], align 4
+; CHECK-NEXT: [[ADD_3:%.*]] = add i32 [[ADD_1]], [[PRE_NEXT]]
+; CHECK-NEXT: [[ADD_4:%.*]] = add i32 [[ADD_2]], [[ADD_3]]
+; CHECK-NEXT: [[IDX_2:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[IV]]
+; CHECK-NEXT: store i32 [[ADD_4]], i32* [[IDX_2]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[FOR]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
-; CHECK-LABEL: preheader: ; preds = %entry
-; CHECK: br label %for
-; CHECK-LABEL: for: ; preds = %for, %preheader
-; CHECK: br i1 %exitcond, label %exit, label %for
-; CHECK-LABEL: exit:
-; CHECK-NEXT: ret void
entry:
br label %preheader
@@ -158,19 +234,32 @@ exit:
; FIXME: We can sink a store, if we can guarantee that it does not alias any
; loads/stores in between.
define void @cannot_sink_store(i32 %x, i32* %ptr, i64 %tc) {
-; CHECK-LABEL: define void @cannot_sink_store(
-; CHECK-NEXT: entry:
-; CHECK-NEXT: br label %preheader
+; CHECK-LABEL: @cannot_sink_store(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[PREHEADER:%.*]]
+; CHECK: preheader:
+; CHECK-NEXT: [[IDX_PHI_TRANS:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
+; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* [[IDX_PHI_TRANS]], align 4
+; CHECK-NEXT: br label [[FOR:%.*]]
+; CHECK: for:
+; CHECK-NEXT: [[PRE_PHI:%.*]] = phi i32 [ [[DOTPRE]], [[PREHEADER]] ], [ [[PRE_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 1, [[PREHEADER]] ], [ [[IV_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[ADD_1:%.*]] = add i32 [[PRE_PHI]], [[X:%.*]]
+; CHECK-NEXT: store i32 [[ADD_1]], i32* [[PTR:%.*]], align 4
+; CHECK-NEXT: [[IDX_1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[IV]]
+; CHECK-NEXT: [[PRE_NEXT]] = load i32, i32* [[IDX_1]], align 4
+; CHECK-NEXT: [[ADD_2:%.*]] = add i32 [[ADD_1]], [[PRE_NEXT]]
+; CHECK-NEXT: [[IDX_2:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[IV]]
+; CHECK-NEXT: store i32 [[ADD_2]], i32* [[IDX_2]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[FOR]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
-; CHECK-LABEL: preheader: ; preds = %entry
-; CHECK: br label %for
-; CHECK-LABEL: for: ; preds = %for, %preheader
-; CHECK: br i1 %exitcond, label %exit, label %for
-; CHECK-LABEL: exit:
-; CHECK-NEXT: ret void
-;
entry:
br label %preheader
@@ -200,19 +289,32 @@ exit:
; Some kinds of reductions are not detected by IVDescriptors. If we have a
; cycle, we cannot sink it.
define void @cannot_sink_reduction(i32 %x, i32* %ptr, i64 %tc) {
-; CHECK-LABEL: define void @cannot_sink_reduction(
-; CHECK-NEXT: entry:
-; CHECK-NEXT: br label %preheader
+; CHECK-LABEL: @cannot_sink_reduction(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[PREHEADER:%.*]]
+; CHECK: preheader:
+; CHECK-NEXT: [[IDX_PHI_TRANS:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 1
+; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* [[IDX_PHI_TRANS]], align 4
+; CHECK-NEXT: br label [[FOR:%.*]]
+; CHECK: for:
+; CHECK-NEXT: [[PRE_PHI:%.*]] = phi i32 [ [[DOTPRE]], [[PREHEADER]] ], [ [[D:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 1, [[PREHEADER]] ], [ [[IV_NEXT:%.*]], [[FOR]] ]
+; CHECK-NEXT: [[D]] = sdiv i32 [[PRE_PHI]], [[X:%.*]]
+; CHECK-NEXT: [[IDX_1:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @p, i64 0, i64 [[IV]]
+; CHECK-NEXT: [[PRE_NEXT:%.*]] = load i32, i32* [[IDX_1]], align 4
+; CHECK-NEXT: [[ADD_2:%.*]] = add i32 [[X]], [[PRE_NEXT]]
+; CHECK-NEXT: [[IDX_2:%.*]] = getelementptr inbounds [257 x i32], [257 x i32]* @q, i64 0, i64 [[IV]]
+; CHECK-NEXT: store i32 [[ADD_2]], i32* [[IDX_2]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], 2000
+; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[FOR]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
-; CHECK-LABEL: preheader: ; preds = %entry
-; CHECK: br label %for
-; CHECK-LABEL: for: ; preds = %for, %preheader
-; CHECK: br i1 %exitcond, label %exit, label %for
-; CHECK-LABEL: exit: ; preds = %for
; CHECK-NET: ret void
-;
entry:
br label %preheader
@@ -240,16 +342,24 @@ exit:
; TODO: We should be able to sink %tmp38 after %tmp60.
define void @instruction_with_2_FOR_operands() {
-; CHECK-LABEL: define void @instruction_with_2_FOR_operands(
-; CHECK-NEXT: bb:
-; CHECK-NEXT: br label %bb13
-
-; CHECK-LABEL: bb13:
-; CHECK: br i1 %tmp12, label %bb13, label %bb74
-
-; CHECK-LABEL: bb74:
+; CHECK-LABEL: @instruction_with_2_FOR_operands(
+; CHECK-NEXT: bb:
+; CHECK-NEXT: br label [[BB13:%.*]]
+; CHECK: bb13:
+; CHECK-NEXT: [[TMP37:%.*]] = phi float [ [[TMP60:%.*]], [[BB13]] ], [ undef, [[BB:%.*]] ]
+; CHECK-NEXT: [[TMP27:%.*]] = phi float [ [[TMP49:%.*]], [[BB13]] ], [ undef, [[BB]] ]
+; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[BB13]] ], [ 0, [[BB]] ]
+; CHECK-NEXT: [[TMP38:%.*]] = fmul fast float [[TMP37]], [[TMP27]]
+; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT: [[TMP49]] = load float, float* undef, align 4
+; CHECK-NEXT: [[TMP60]] = load float, float* undef, align 4
+; CHECK-NEXT: [[TMP12:%.*]] = icmp slt i64 [[INDVARS_IV]], undef
+; CHECK-NEXT: br i1 [[TMP12]], label [[BB13]], label [[BB74:%.*]]
+; CHECK: bb74:
; CHECK-NEXT: ret void
;
+
+
bb:
br label %bb13
@@ -270,8 +380,30 @@ bb74: ; preds = %bb13
; Users that are phi nodes cannot be sunk.
define void @cannot_sink_phi(i32* %ptr) {
-; CHECK-LABEL: define void @cannot_sink_phi(
-; CHECK-NOT: vector.body
+; CHECK-LABEL: @cannot_sink_phi(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[LOOP_HEADER:%.*]]
+; CHECK: loop.header:
+; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 1, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
+; CHECK-NEXT: [[FOR:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[FOR_NEXT:%.*]], [[LOOP_LATCH]] ]
+; CHECK-NEXT: [[C_1:%.*]] = icmp ult i64 [[IV]], 500
+; CHECK-NEXT: br i1 [[C_1]], label [[IF_TRUEBB:%.*]], label [[IF_FALSEBB:%.*]]
+; CHECK: if.truebb:
+; CHECK-NEXT: br label [[LOOP_LATCH]]
+; CHECK: if.falsebb:
+; CHECK-NEXT: br label [[LOOP_LATCH]]
+; CHECK: loop.latch:
+; CHECK-NEXT: [[FIRST_TIME_1:%.*]] = phi i32 [ 20, [[IF_TRUEBB]] ], [ [[FOR]], [[IF_FALSEBB]] ]
+; CHECK-NEXT: [[C_2:%.*]] = icmp ult i64 [[IV]], 800
+; CHECK-NEXT: [[FOR_NEXT]] = select i1 [[C_2]], i32 30, i32 [[FIRST_TIME_1]]
+; CHECK-NEXT: [[PTR_IDX:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[IV]]
+; CHECK-NEXT: store i32 [[FOR_NEXT]], i32* [[PTR_IDX]], align 4
+; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1000
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[EXIT:%.*]], label [[LOOP_HEADER]]
+; CHECK: exit:
+; CHECK-NEXT: ret void
+;
entry:
br label %loop.header
More information about the llvm-commits
mailing list