[llvm] [InstCombine] Don't sink if it would require dropping deref assumptions. (PR #166945)
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Sat Nov 8 06:54:23 PST 2025
https://github.com/fhahn updated https://github.com/llvm/llvm-project/pull/166945
>From bff824ed51516bfb023cd147f512a69f70f81f58 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Fri, 7 Nov 2025 19:30:46 +0000
Subject: [PATCH 1/3] [InstCombine] Add extra tests.
---
.../sink-dereferenceable-assume.ll | 99 ++++++++++++++++++-
1 file changed, 94 insertions(+), 5 deletions(-)
diff --git a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
index 953132309900b..8751a9fe9c174 100644
--- a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
+++ b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
@@ -1,11 +1,11 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -p instcombine -S %s | FileCheck %s
-define i64 @test_sink_with_dereferenceable_assume(ptr %p, ptr %q, i1 %cond) {
-; CHECK-LABEL: define i64 @test_sink_with_dereferenceable_assume(
-; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[COND:%.*]]) {
+define i64 @test_dereferenceable_assume(ptr %p, ptr %q, i1 %c.0) {
+; CHECK-LABEL: define i64 @test_dereferenceable_assume(
+; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
-; CHECK-NEXT: br i1 [[COND]], label %[[THEN:.*]], label %[[ELSE:.*]]
+; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
; CHECK: [[THEN]]:
; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
@@ -19,7 +19,7 @@ entry:
%q_int = ptrtoint ptr %q to i64
%diff = sub i64 %q_int, %p_int
call void @llvm.assume(i1 true) [ "dereferenceable"(ptr %p, i64 %diff) ]
- br i1 %cond, label %then, label %else
+ br i1 %c.0, label %then, label %else
then:
ret i64 %diff
@@ -28,4 +28,93 @@ else:
ret i64 0
}
+define i64 @test_sink_with_dereferenceable_assume_same_block_as_user(ptr %p, ptr %q, i1 %c.0) {
+; CHECK-LABEL: define i64 @test_sink_with_dereferenceable_assume_same_block_as_user(
+; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
+; CHECK: [[THEN]]:
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
+; CHECK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(ptr [[P]], i64 [[DIFF]]) ]
+; CHECK-NEXT: ret i64 [[DIFF]]
+; CHECK: [[ELSE]]:
+; CHECK-NEXT: ret i64 0
+;
+entry:
+ %p_int = ptrtoint ptr %p to i64
+ %q_int = ptrtoint ptr %q to i64
+ %diff = sub i64 %q_int, %p_int
+ br i1 %c.0, label %then, label %else
+
+then:
+ call void @llvm.assume(i1 true) [ "dereferenceable"(ptr %p, i64 %diff) ]
+ ret i64 %diff
+
+else:
+ ret i64 0
+}
+
+define i64 @test_sink_with_multiple_users_dominated_by_deref(ptr %p, ptr %q, i1 %c.0, i1 %c.1) {
+; CHECK-LABEL: define i64 @test_sink_with_multiple_users_dominated_by_deref(
+; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]], i1 [[C_1:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
+; CHECK: [[THEN]]:
+; CHECK-NEXT: br i1 [[C_1]], label %[[THEN_2:.*]], label %[[ELSE]]
+; CHECK: [[THEN_2]]:
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
+; CHECK-NEXT: [[DOUBLED:%.*]] = shl i64 [[DIFF]], 1
+; CHECK-NEXT: ret i64 [[DOUBLED]]
+; CHECK: [[ELSE]]:
+; CHECK-NEXT: ret i64 0
+;
+entry:
+ %p_int = ptrtoint ptr %p to i64
+ %q_int = ptrtoint ptr %q to i64
+ %diff = sub i64 %q_int, %p_int
+ br i1 %c.0, label %then, label %else
+
+then:
+ call void @llvm.assume(i1 true) [ "dereferenceable"(ptr %p, i64 %diff) ]
+ br i1 %c.1, label %then.2, label %else
+
+then.2:
+ %doubled = mul i64 %diff, 2
+ ret i64 %doubled
+
+else:
+ ret i64 0
+}
+
+define i64 @test_deref_user_does_not_dominate_other_user(ptr %p, ptr %q, i1 %c.0) {
+; CHECK-LABEL: define i64 @test_deref_user_does_not_dominate_other_user(
+; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: br i1 [[C_0]], label %[[MIDDLE:.*]], label %[[EXIT:.*]]
+; CHECK: [[MIDDLE]]:
+; CHECK-NEXT: br label %[[EXIT]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
+; CHECK-NEXT: ret i64 [[DIFF]]
+;
+entry:
+ %p_int = ptrtoint ptr %p to i64
+ %q_int = ptrtoint ptr %q to i64
+ %diff = sub i64 %q_int, %p_int
+ br i1 %c.0, label %middle, label %exit
+
+middle:
+ call void @llvm.assume(i1 true) [ "dereferenceable"(ptr %p, i64 %diff) ]
+ br label %exit
+
+exit:
+ ret i64 %diff
+}
+
declare void @llvm.assume(i1 noundef)
>From 6b524817039d7f076d4389bc4c9136d01abcee7c Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Fri, 7 Nov 2025 13:35:17 +0000
Subject: [PATCH 2/3] [InstCombine] Don't sink if it would require dropping
deref assumptions.
Currently sinking assumes in instcombine drops assumes if they would
prevent sinking. Removing dereferenceable assumptions earlier on can
inhibit vectorization of early-exit loops in practice.
Special-case deferenceable assumptions so that they block sinking. This
can be combined with a separate change to drop dereferencebale
assumptions after vectorization: https://clang.godbolt.org/z/jGqcx3sbs
Not sure if there is a better solution.
---
.../InstCombine/InstructionCombining.cpp | 12 +++
.../sink-dereferenceable-assume.ll | 4 -
.../PhaseOrdering/AArch64/std-find.ll | 102 ++++++++----------
3 files changed, 58 insertions(+), 60 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index b158e0f626850..cea5be2468feb 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -5413,6 +5413,18 @@ bool InstCombinerImpl::tryToSinkInstruction(Instruction *I,
return false;
}
+ // Do not sink if there are dereferenceable assumes that would be removed.
+ for (User *User : I->users()) {
+ auto *CI = dyn_cast<CallInst>(User);
+ if (!CI || CI->getParent() == DestBlock)
+ continue;
+
+ if (CI->getIntrinsicID() == Intrinsic::assume &&
+ CI->getOperandBundle("dereferenceable")) {
+ return false;
+ }
+ }
+
I->dropDroppableUses([&](const Use *U) {
auto *I = dyn_cast<Instruction>(U->getUser());
if (I && I->getParent() != DestBlock) {
diff --git a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
index 8751a9fe9c174..8b9779f3df63a 100644
--- a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
+++ b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
@@ -5,11 +5,7 @@ define i64 @test_dereferenceable_assume(ptr %p, ptr %q, i1 %c.0) {
; CHECK-LABEL: define i64 @test_dereferenceable_assume(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
-; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
; CHECK: [[THEN]]:
-; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
-; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
-; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
; CHECK-NEXT: ret i64 [[DIFF]]
; CHECK: [[ELSE]]:
; CHECK-NEXT: ret i64 0
diff --git a/llvm/test/Transforms/PhaseOrdering/AArch64/std-find.ll b/llvm/test/Transforms/PhaseOrdering/AArch64/std-find.ll
index 33e3e83770e7f..e9149795954ec 100644
--- a/llvm/test/Transforms/PhaseOrdering/AArch64/std-find.ll
+++ b/llvm/test/Transforms/PhaseOrdering/AArch64/std-find.ll
@@ -133,75 +133,65 @@ define ptr @std_find_caller(ptr noundef %first, ptr noundef %last) {
; CHECK-LABEL: define noundef ptr @std_find_caller(
; CHECK-SAME: ptr noundef [[FIRST:%.*]], ptr noundef [[LAST:%.*]]) local_unnamed_addr #[[ATTR0]] {
; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: [[FIRST3:%.*]] = ptrtoint ptr [[FIRST]] to i64
+; CHECK-NEXT: [[LAST_I64:%.*]] = ptrtoint ptr [[LAST]] to i64
+; CHECK-NEXT: [[PTR_SUB:%.*]] = sub i64 [[LAST_I64]], [[FIRST3]]
; CHECK-NEXT: call void @llvm.assume(i1 true) [ "align"(ptr [[FIRST]], i64 2) ]
; CHECK-NEXT: call void @llvm.assume(i1 true) [ "align"(ptr [[LAST]], i64 2) ]
+; CHECK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(ptr [[FIRST]], i64 [[PTR_SUB]]) ]
; CHECK-NEXT: [[PRE_I:%.*]] = icmp eq ptr [[FIRST]], [[LAST]]
; CHECK-NEXT: br i1 [[PRE_I]], label %[[STD_FIND_GENERIC_IMPL_EXIT:.*]], label %[[LOOP_HEADER_I_PREHEADER:.*]]
; CHECK: [[LOOP_HEADER_I_PREHEADER]]:
-; CHECK-NEXT: [[LAST2:%.*]] = ptrtoint ptr [[LAST]] to i64
-; CHECK-NEXT: [[FIRST3:%.*]] = ptrtoint ptr [[FIRST]] to i64
-; CHECK-NEXT: [[LAST_I64:%.*]] = ptrtoint ptr [[LAST]] to i64
-; CHECK-NEXT: [[FIRST1:%.*]] = ptrtoint ptr [[FIRST]] to i64
-; CHECK-NEXT: [[PTR_SUB:%.*]] = sub i64 [[LAST_I64]], [[FIRST1]]
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[FIRST]], i64 [[PTR_SUB]]
-; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[LAST2]], -2
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[LAST_I64]], -2
; CHECK-NEXT: [[TMP1:%.*]] = sub i64 [[TMP0]], [[FIRST3]]
; CHECK-NEXT: [[TMP2:%.*]] = lshr exact i64 [[TMP1]], 1
; CHECK-NEXT: [[TMP3:%.*]] = add nuw i64 [[TMP2]], 1
-; CHECK-NEXT: [[XTRAITER:%.*]] = and i64 [[TMP3]], 3
-; CHECK-NEXT: [[TMP4:%.*]] = and i64 [[TMP1]], 6
-; CHECK-NEXT: [[LCMP_MOD_NOT:%.*]] = icmp eq i64 [[TMP4]], 6
-; CHECK-NEXT: br i1 [[LCMP_MOD_NOT]], label %[[LOOP_HEADER_I_PROL_LOOPEXIT:.*]], label %[[LOOP_HEADER_I_PROL:.*]]
-; CHECK: [[LOOP_HEADER_I_PROL]]:
-; CHECK-NEXT: [[PTR_IV_I_PROL:%.*]] = phi ptr [ [[PTR_IV_NEXT_I_PROL:%.*]], %[[LOOP_LATCH_I_PROL:.*]] ], [ [[FIRST]], %[[LOOP_HEADER_I_PREHEADER]] ]
-; CHECK-NEXT: [[PROL_ITER:%.*]] = phi i64 [ [[PROL_ITER_NEXT:%.*]], %[[LOOP_LATCH_I_PROL]] ], [ 0, %[[LOOP_HEADER_I_PREHEADER]] ]
-; CHECK-NEXT: [[L_I_PROL:%.*]] = load i16, ptr [[PTR_IV_I_PROL]], align 2
-; CHECK-NEXT: [[C_1_I_PROL:%.*]] = icmp eq i16 [[L_I_PROL]], 1
-; CHECK-NEXT: br i1 [[C_1_I_PROL]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_LATCH_I_PROL]]
-; CHECK: [[LOOP_LATCH_I_PROL]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_PROL]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I_PROL]], i64 2
-; CHECK-NEXT: [[PROL_ITER_NEXT]] = add i64 [[PROL_ITER]], 1
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 158
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[LOOP_HEADER_I_PREHEADER2:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: [[XTRAITER:%.*]] = and i64 [[TMP3]], -8
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[PROL_ITER_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[OFFSET_IDX:%.*]] = shl i64 [[INDEX]], 1
+; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[FIRST]], i64 [[OFFSET_IDX]]
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i16>, ptr [[NEXT_GEP]], align 2
+; CHECK-NEXT: [[WIDE_LOAD_FR:%.*]] = freeze <8 x i16> [[WIDE_LOAD]]
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq <8 x i16> [[WIDE_LOAD_FR]], splat (i16 1)
+; CHECK-NEXT: [[PROL_ITER_NEXT]] = add nuw i64 [[INDEX]], 8
+; CHECK-NEXT: [[TMP5:%.*]] = bitcast <8 x i1> [[TMP4]] to i8
+; CHECK-NEXT: [[TMP6:%.*]] = icmp ne i8 [[TMP5]], 0
; CHECK-NEXT: [[PROL_ITER_CMP_NOT:%.*]] = icmp eq i64 [[PROL_ITER_NEXT]], [[XTRAITER]]
-; CHECK-NEXT: br i1 [[PROL_ITER_CMP_NOT]], label %[[LOOP_HEADER_I_PROL_LOOPEXIT]], label %[[LOOP_HEADER_I_PROL]], !llvm.loop [[LOOP3:![0-9]+]]
-; CHECK: [[LOOP_HEADER_I_PROL_LOOPEXIT]]:
-; CHECK-NEXT: [[PTR_IV_I_UNR:%.*]] = phi ptr [ [[FIRST]], %[[LOOP_HEADER_I_PREHEADER]] ], [ [[PTR_IV_NEXT_I_PROL]], %[[LOOP_LATCH_I_PROL]] ]
-; CHECK-NEXT: [[TMP5:%.*]] = icmp ult i64 [[TMP1]], 6
-; CHECK-NEXT: br i1 [[TMP5]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_HEADER_I:.*]]
+; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[PROL_ITER_CMP_NOT]]
+; CHECK-NEXT: br i1 [[TMP8]], label %[[MIDDLE_SPLIT:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK: [[MIDDLE_SPLIT]]:
+; CHECK-NEXT: [[TMP9:%.*]] = shl i64 [[XTRAITER]], 1
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr i8, ptr [[FIRST]], i64 [[TMP9]]
+; CHECK-NEXT: br i1 [[TMP6]], label %[[VECTOR_EARLY_EXIT:.*]], label %[[MIDDLE_BLOCK:.*]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[XTRAITER]]
+; CHECK-NEXT: br i1 [[CMP_N]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_HEADER_I_PREHEADER2]]
+; CHECK: [[LOOP_HEADER_I_PREHEADER2]]:
+; CHECK-NEXT: [[PTR_IV_I_PH:%.*]] = phi ptr [ [[FIRST]], %[[LOOP_HEADER_I_PREHEADER]] ], [ [[TMP10]], %[[MIDDLE_BLOCK]] ]
+; CHECK-NEXT: br label %[[LOOP_HEADER_I:.*]]
+; CHECK: [[VECTOR_EARLY_EXIT]]:
+; CHECK-NEXT: [[TMP11:%.*]] = tail call i64 @llvm.experimental.cttz.elts.i64.v8i1(<8 x i1> [[TMP4]], i1 true)
+; CHECK-NEXT: [[TMP12:%.*]] = add i64 [[INDEX]], [[TMP11]]
+; CHECK-NEXT: [[TMP13:%.*]] = shl i64 [[TMP12]], 1
+; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i8, ptr [[FIRST]], i64 [[TMP13]]
+; CHECK-NEXT: br label %[[STD_FIND_GENERIC_IMPL_EXIT]]
; CHECK: [[LOOP_HEADER_I]]:
-; CHECK-NEXT: [[PTR_IV_I:%.*]] = phi ptr [ [[PTR_IV_NEXT_I_3:%.*]], %[[LOOP_LATCH_I_3:.*]] ], [ [[PTR_IV_I_UNR]], %[[LOOP_HEADER_I_PROL_LOOPEXIT]] ]
+; CHECK-NEXT: [[PTR_IV_I:%.*]] = phi ptr [ [[PTR_IV_NEXT_I:%.*]], %[[LOOP_LATCH_I:.*]] ], [ [[PTR_IV_I_PH]], %[[LOOP_HEADER_I_PREHEADER2]] ]
; CHECK-NEXT: [[L_I:%.*]] = load i16, ptr [[PTR_IV_I]], align 2
; CHECK-NEXT: [[C_1_I:%.*]] = icmp eq i16 [[L_I]], 1
-; CHECK-NEXT: br i1 [[C_1_I]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_LATCH_I:.*]]
+; CHECK-NEXT: br i1 [[C_1_I]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_LATCH_I]]
; CHECK: [[LOOP_LATCH_I]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 2
-; CHECK-NEXT: [[L_I_1:%.*]] = load i16, ptr [[PTR_IV_NEXT_I]], align 2
-; CHECK-NEXT: [[C_1_I_1:%.*]] = icmp eq i16 [[L_I_1]], 1
-; CHECK-NEXT: br i1 [[C_1_I_1]], label %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT11:.*]], label %[[LOOP_LATCH_I_1:.*]]
-; CHECK: [[LOOP_LATCH_I_1]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_1:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 4
-; CHECK-NEXT: [[L_I_2:%.*]] = load i16, ptr [[PTR_IV_NEXT_I_1]], align 2
-; CHECK-NEXT: [[C_1_I_2:%.*]] = icmp eq i16 [[L_I_2]], 1
-; CHECK-NEXT: br i1 [[C_1_I_2]], label %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT9:.*]], label %[[LOOP_LATCH_I_2:.*]]
-; CHECK: [[LOOP_LATCH_I_2]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_2:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 6
-; CHECK-NEXT: [[L_I_3:%.*]] = load i16, ptr [[PTR_IV_NEXT_I_2]], align 2
-; CHECK-NEXT: [[C_1_I_3:%.*]] = icmp eq i16 [[L_I_3]], 1
-; CHECK-NEXT: br i1 [[C_1_I_3]], label %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT7:.*]], label %[[LOOP_LATCH_I_3]]
-; CHECK: [[LOOP_LATCH_I_3]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_3]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 8
-; CHECK-NEXT: [[EC_I_3:%.*]] = icmp eq ptr [[PTR_IV_NEXT_I_3]], [[LAST]]
-; CHECK-NEXT: br i1 [[EC_I_3]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_HEADER_I]]
-; CHECK: [[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT7]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_2_LE:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 6
-; CHECK-NEXT: br label %[[STD_FIND_GENERIC_IMPL_EXIT]]
-; CHECK: [[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT9]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_1_LE:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 4
-; CHECK-NEXT: br label %[[STD_FIND_GENERIC_IMPL_EXIT]]
-; CHECK: [[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT11]]:
-; CHECK-NEXT: [[PTR_IV_NEXT_I_LE:%.*]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 2
-; CHECK-NEXT: br label %[[STD_FIND_GENERIC_IMPL_EXIT]]
+; CHECK-NEXT: [[PTR_IV_NEXT_I]] = getelementptr inbounds nuw i8, ptr [[PTR_IV_I]], i64 2
+; CHECK-NEXT: [[EC_I:%.*]] = icmp eq ptr [[PTR_IV_NEXT_I]], [[LAST]]
+; CHECK-NEXT: br i1 [[EC_I]], label %[[STD_FIND_GENERIC_IMPL_EXIT]], label %[[LOOP_HEADER_I]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[STD_FIND_GENERIC_IMPL_EXIT]]:
-; CHECK-NEXT: [[RES_I:%.*]] = phi ptr [ [[FIRST]], %[[ENTRY]] ], [ [[SCEVGEP]], %[[LOOP_HEADER_I_PROL_LOOPEXIT]] ], [ [[PTR_IV_NEXT_I_2_LE]], %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT7]] ], [ [[PTR_IV_NEXT_I_1_LE]], %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT9]] ], [ [[PTR_IV_NEXT_I_LE]], %[[STD_FIND_GENERIC_IMPL_EXIT_LOOPEXIT_UNR_LCSSA_LOOPEXIT_SPLIT_LOOP_EXIT11]] ], [ [[SCEVGEP]], %[[LOOP_LATCH_I_3]] ], [ [[PTR_IV_I]], %[[LOOP_HEADER_I]] ], [ [[PTR_IV_I_PROL]], %[[LOOP_HEADER_I_PROL]] ]
+; CHECK-NEXT: [[RES_I:%.*]] = phi ptr [ [[FIRST]], %[[ENTRY]] ], [ [[SCEVGEP]], %[[MIDDLE_BLOCK]] ], [ [[TMP14]], %[[VECTOR_EARLY_EXIT]] ], [ [[SCEVGEP]], %[[LOOP_LATCH_I]] ], [ [[PTR_IV_I]], %[[LOOP_HEADER_I]] ]
; CHECK-NEXT: ret ptr [[RES_I]]
;
entry:
@@ -241,6 +231,6 @@ declare void @llvm.assume(i1 noundef)
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
-; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META4:![0-9]+]]}
-; CHECK: [[META4]] = !{!"llvm.loop.unroll.disable"}
+; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META2]], [[META1]]}
;.
>From ae29bfe2b1a55b4c9058f8038ce278db0c3be009 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo at fhahn.com>
Date: Fri, 7 Nov 2025 19:27:34 +0000
Subject: [PATCH 3/3] !fixup move code to getOptionalSinkBlockForInst.
---
.../InstCombine/InstructionCombining.cpp | 23 ++++++++-----------
.../sink-dereferenceable-assume.ll | 19 ++++++++++-----
2 files changed, 22 insertions(+), 20 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
index cea5be2468feb..fbefd4ab84d99 100644
--- a/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstructionCombining.cpp
@@ -5413,18 +5413,6 @@ bool InstCombinerImpl::tryToSinkInstruction(Instruction *I,
return false;
}
- // Do not sink if there are dereferenceable assumes that would be removed.
- for (User *User : I->users()) {
- auto *CI = dyn_cast<CallInst>(User);
- if (!CI || CI->getParent() == DestBlock)
- continue;
-
- if (CI->getIntrinsicID() == Intrinsic::assume &&
- CI->getOperandBundle("dereferenceable")) {
- return false;
- }
- }
-
I->dropDroppableUses([&](const Use *U) {
auto *I = dyn_cast<Instruction>(U->getUser());
if (I && I->getParent() != DestBlock) {
@@ -5636,8 +5624,15 @@ bool InstCombinerImpl::run() {
for (Use &U : I->uses()) {
User *User = U.getUser();
- if (User->isDroppable())
- continue;
+ if (User->isDroppable()) {
+ // Do not sink if there are dereferenceable assumes that would be
+ // removed.
+ auto II = dyn_cast<IntrinsicInst>(User);
+ if (II->getIntrinsicID() != Intrinsic::assume ||
+ !II->getOperandBundle("dereferenceable"))
+ continue;
+ }
+
if (NumUsers > MaxSinkNumUsers)
return std::nullopt;
diff --git a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
index 8b9779f3df63a..8ceb310fc8f71 100644
--- a/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
+++ b/llvm/test/Transforms/InstCombine/sink-dereferenceable-assume.ll
@@ -5,6 +5,11 @@ define i64 @test_dereferenceable_assume(ptr %p, ptr %q, i1 %c.0) {
; CHECK-LABEL: define i64 @test_dereferenceable_assume(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
+; CHECK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(ptr [[P]], i64 [[DIFF]]) ]
+; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
; CHECK: [[THEN]]:
; CHECK-NEXT: ret i64 [[DIFF]]
; CHECK: [[ELSE]]:
@@ -56,13 +61,14 @@ define i64 @test_sink_with_multiple_users_dominated_by_deref(ptr %p, ptr %q, i1
; CHECK-LABEL: define i64 @test_sink_with_multiple_users_dominated_by_deref(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]], i1 [[C_1:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
; CHECK-NEXT: br i1 [[C_0]], label %[[THEN:.*]], label %[[ELSE:.*]]
; CHECK: [[THEN]]:
+; CHECK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(ptr [[P]], i64 [[DIFF]]) ]
; CHECK-NEXT: br i1 [[C_1]], label %[[THEN_2:.*]], label %[[ELSE]]
; CHECK: [[THEN_2]]:
-; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
-; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
-; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
; CHECK-NEXT: [[DOUBLED:%.*]] = shl i64 [[DIFF]], 1
; CHECK-NEXT: ret i64 [[DOUBLED]]
; CHECK: [[ELSE]]:
@@ -90,13 +96,14 @@ define i64 @test_deref_user_does_not_dominate_other_user(ptr %p, ptr %q, i1 %c.0
; CHECK-LABEL: define i64 @test_deref_user_does_not_dominate_other_user(
; CHECK-SAME: ptr [[P:%.*]], ptr [[Q:%.*]], i1 [[C_0:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
+; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
+; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
+; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
; CHECK-NEXT: br i1 [[C_0]], label %[[MIDDLE:.*]], label %[[EXIT:.*]]
; CHECK: [[MIDDLE]]:
+; CHECK-NEXT: call void @llvm.assume(i1 true) [ "dereferenceable"(ptr [[P]], i64 [[DIFF]]) ]
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
-; CHECK-NEXT: [[Q_INT:%.*]] = ptrtoint ptr [[Q]] to i64
-; CHECK-NEXT: [[P_INT:%.*]] = ptrtoint ptr [[P]] to i64
-; CHECK-NEXT: [[DIFF:%.*]] = sub i64 [[Q_INT]], [[P_INT]]
; CHECK-NEXT: ret i64 [[DIFF]]
;
entry:
More information about the llvm-commits
mailing list