[llvm-branch-commits] [llvm] [BOLT][docs] Expand Heatmaps.md (PR #98162)
paschalis-mpeis wrote: Thanks for your review @aaupov . This is a stacked pull request as the updated docs refer to the `-print-mappings` option. So it will be merged after: - #97567 https://github.com/llvm/llvm-project/pull/98162 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [NFC][BOLT] Rename createDummyReturnFunction to createReturnBody (PR #98448)
https://github.com/paschalis-mpeis updated
https://github.com/llvm/llvm-project/pull/98448
>From 2e9d663a9a164735fbe1a2408994acc1abaa8c21 Mon Sep 17 00:00:00 2001
From: Paschalis Mpeis
Date: Thu, 11 Jul 2024 09:32:12 +0100
Subject: [PATCH] [NFC][BOLT] Rename createDummyReturnFunction to
createReturnInstructionList
createDummyReturnFunction is not creating a function but instead only
a function body that is simply a return statement.
This patch renames it to:
createReturnInstructionList
---
bolt/include/bolt/Core/MCPlusBuilder.h | 3 ++-
bolt/lib/Passes/Instrumentation.cpp| 2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/bolt/include/bolt/Core/MCPlusBuilder.h
b/bolt/include/bolt/Core/MCPlusBuilder.h
index 885d627f7b64f..c916c6f95751f 100644
--- a/bolt/include/bolt/Core/MCPlusBuilder.h
+++ b/bolt/include/bolt/Core/MCPlusBuilder.h
@@ -2044,7 +2044,8 @@ class MCPlusBuilder {
/// Returns a function body that contains only a return instruction. An
/// example usage is a workaround for the '__bolt_fini_trampoline' of
// Instrumentation.
- virtual InstructionListType createDummyReturnFunction(MCContext *Ctx) const {
+ virtual InstructionListType
+ createReturnInstructionList(MCContext *Ctx) const {
InstructionListType Insts(1);
createReturn(Insts[0]);
return Insts;
diff --git a/bolt/lib/Passes/Instrumentation.cpp
b/bolt/lib/Passes/Instrumentation.cpp
index e824a42d82696..ebb3925749b4d 100644
--- a/bolt/lib/Passes/Instrumentation.cpp
+++ b/bolt/lib/Passes/Instrumentation.cpp
@@ -754,7 +754,7 @@ void
Instrumentation::createAuxiliaryFunctions(BinaryContext &BC) {
// with unknown symbol in runtime library. E.g. for static PIE
// executable
createSimpleFunction("__bolt_fini_trampoline",
- BC.MIB->createDummyReturnFunction(BC.Ctx.get()));
+ BC.MIB->createReturnInstructionList(BC.Ctx.get()));
}
}
}
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] [NFC][BOLT] Rename createDummyReturnFunction to createReturnBody (PR #98448)
https://github.com/paschalis-mpeis edited https://github.com/llvm/llvm-project/pull/98448 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] NFC][BOLT] Rename createDummyReturnFunction to createReturnInstructionList (PR #98448)
https://github.com/paschalis-mpeis edited https://github.com/llvm/llvm-project/pull/98448 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] NFC][BOLT] Rename createDummyReturnFunction to createReturnInstructi.. (PR #98448)
https://github.com/paschalis-mpeis edited https://github.com/llvm/llvm-project/pull/98448 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [llvm] NFC][BOLT] Rename createDummyReturnFunction to createReturnInstructi.. (PR #98448)
paschalis-mpeis wrote: Rebased on top of the updated #96626 Thanks for suggesting `createReturnInstructionList`; I think it's better so I used it. https://github.com/llvm/llvm-project/pull/98448 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [flang] 017a499 - Revert "[flang] Adjust semantics of the char length of an array constructor (…"
Author: David Spickett
Date: 2024-07-12T11:34:32+01:00
New Revision: 017a49990189cc9513ff088eebbeeb1f54e3ff93
URL:
https://github.com/llvm/llvm-project/commit/017a49990189cc9513ff088eebbeeb1f54e3ff93
DIFF:
https://github.com/llvm/llvm-project/commit/017a49990189cc9513ff088eebbeeb1f54e3ff93.diff
LOG: Revert "[flang] Adjust semantics of the char length of an array
constructor (…"
This reverts commit 2d7e136fc0e31207b962397250bc1581203c8d59.
Added:
Modified:
flang/lib/Semantics/expression.cpp
flang/test/Lower/HLFIR/array-ctor-character.f90
flang/test/Semantics/array-constr-len.f90
Removed:
diff --git a/flang/lib/Semantics/expression.cpp
b/flang/lib/Semantics/expression.cpp
index 844ffd44604ba..90900d9acb6ad 100644
--- a/flang/lib/Semantics/expression.cpp
+++ b/flang/lib/Semantics/expression.cpp
@@ -1584,8 +1584,7 @@ class ArrayConstructorContext {
std::optional> LengthIfGood() const {
if (type_) {
auto len{type_->LEN()};
- if (explicitType_ ||
- (len && IsConstantExpr(*len) && !ContainsAnyImpliedDoIndex(*len))) {
+ if (len && IsConstantExpr(*len) && !ContainsAnyImpliedDoIndex(*len)) {
return len;
}
}
diff --git a/flang/test/Lower/HLFIR/array-ctor-character.f90
b/flang/test/Lower/HLFIR/array-ctor-character.f90
index 881085b370ffe..85e6ed27fe077 100644
--- a/flang/test/Lower/HLFIR/array-ctor-character.f90
+++ b/flang/test/Lower/HLFIR/array-ctor-character.f90
@@ -93,11 +93,10 @@ subroutine test_set_length_sanitize(i, c1)
call takes_char([character(len=i):: c1])
end subroutine
! CHECK-LABEL: func.func @_QPtest_set_length_sanitize(
-! CHECK: %[[VAL_2:.*]]:2 = hlfir.declare {{.*}}Ec1
-! CHECK: %[[VAL_3:.*]]:2 = hlfir.declare %arg0
-! CHECK: %[[VAL_4:.*]] = fir.load %[[VAL_3]]#0 : !fir.ref
-! CHECK: %[[VAL_25:.*]] = fir.load %[[VAL_3]]#0 : !fir.ref
+! CHECK: %[[VAL_6:.*]]:2 = hlfir.declare {{.*}}Ec1
+! CHECK: %[[VAL_9:.*]]:2 = hlfir.declare {{.*}}Ei
+! CHECK: %[[VAL_25:.*]] = fir.load %[[VAL_9]]#0 : !fir.ref
! CHECK: %[[VAL_26:.*]] = arith.constant 0 : i64
! CHECK: %[[VAL_27:.*]] = arith.cmpi sgt, %[[VAL_25]], %[[VAL_26]] : i64
! CHECK: %[[VAL_28:.*]] = arith.select %[[VAL_27]], %[[VAL_25]], %[[VAL_26]]
: i64
-! CHECK: %[[VAL_29:.*]] = hlfir.set_length %[[VAL_2]]#0 len %[[VAL_28]] :
(!fir.boxchar<1>, i64) -> !hlfir.expr>
+! CHECK: %[[VAL_29:.*]] = hlfir.set_length %[[VAL_6]]#0 len %[[VAL_28]] :
(!fir.boxchar<1>, i64) -> !hlfir.expr>
diff --git a/flang/test/Semantics/array-constr-len.f90
b/flang/test/Semantics/array-constr-len.f90
index 4de9c76c7041c..a785c9e2ece6d 100644
--- a/flang/test/Semantics/array-constr-len.f90
+++ b/flang/test/Semantics/array-constr-len.f90
@@ -10,5 +10,6 @@ subroutine subr(s,n)
print *, [(s(1:j),j=1,0)]
print *, [(s(1:1),j=1,0)] ! ok
print *, [character(2)::(s(1:n),j=1,0)] ! ok
+ !ERROR: Array constructor implied DO loop has no iterations and
indeterminate character length
print *, [character(n)::(s(1:n),j=1,0)]
end
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] f1a5264 - Revert "[clang] Catch missing format attributes (#70024)"
Author: Aaron Ballman
Date: 2024-07-12T06:57:49-04:00
New Revision: f1a52644e84021dded1fa5e58401cf23b8c519e6
URL:
https://github.com/llvm/llvm-project/commit/f1a52644e84021dded1fa5e58401cf23b8c519e6
DIFF:
https://github.com/llvm/llvm-project/commit/f1a52644e84021dded1fa5e58401cf23b8c519e6.diff
LOG: Revert "[clang] Catch missing format attributes (#70024)"
This reverts commit 70f57d25743ca7230bcad3cae7e3072f0aded6f7.
Added:
Modified:
clang/docs/ReleaseNotes.rst
clang/include/clang/Basic/DiagnosticGroups.td
clang/include/clang/Basic/DiagnosticSemaKinds.td
clang/include/clang/Sema/Attr.h
clang/include/clang/Sema/Sema.h
clang/lib/Sema/SemaDecl.cpp
clang/lib/Sema/SemaDeclAttr.cpp
Removed:
clang/test/Sema/attr-format-missing.c
clang/test/Sema/attr-format-missing.cpp
diff --git a/clang/docs/ReleaseNotes.rst b/clang/docs/ReleaseNotes.rst
index afcd3c655f0f6..781fc8ab1de1e 100644
--- a/clang/docs/ReleaseNotes.rst
+++ b/clang/docs/ReleaseNotes.rst
@@ -716,9 +716,6 @@ Improvements to Clang's diagnostics
- Clang now diagnoses integer constant expressions that are folded to a
constant value as an extension in more circumstances. Fixes #GH59863
-- Clang now diagnoses missing format attributes for non-template functions and
- class/struct/union members. Fixes #GH60718
-
Improvements to Clang's time-trace
--
diff --git a/clang/include/clang/Basic/DiagnosticGroups.td
b/clang/include/clang/Basic/DiagnosticGroups.td
index da6a3b2fe3571..2241f8481484e 100644
--- a/clang/include/clang/Basic/DiagnosticGroups.td
+++ b/clang/include/clang/Basic/DiagnosticGroups.td
@@ -525,6 +525,7 @@ def MainReturnType : DiagGroup<"main-return-type">;
def MaxUnsignedZero : DiagGroup<"max-unsigned-zero">;
def MissingBraces : DiagGroup<"missing-braces">;
def MissingDeclarations: DiagGroup<"missing-declarations">;
+def : DiagGroup<"missing-format-attribute">;
def MissingIncludeDirs : DiagGroup<"missing-include-dirs">;
def MissingNoreturn : DiagGroup<"missing-noreturn">;
def MultiChar : DiagGroup<"multichar">;
diff --git a/clang/include/clang/Basic/DiagnosticSemaKinds.td
b/clang/include/clang/Basic/DiagnosticSemaKinds.td
index f5c18edb65217..0ea3677355169 100644
--- a/clang/include/clang/Basic/DiagnosticSemaKinds.td
+++ b/clang/include/clang/Basic/DiagnosticSemaKinds.td
@@ -1031,9 +1031,6 @@ def err_opencl_invalid_param : Error<
def err_opencl_invalid_return : Error<
"declaring function return value of type %0 is not allowed %select{; did you
forget * ?|}1">;
def warn_enum_value_overflow : Warning<"overflow in enumeration value">;
-def warn_missing_format_attribute : Warning<
- "diagnostic behavior may be improved by adding the %0 format attribute to
the declaration of %1">,
- InGroup>, DefaultIgnore;
def warn_pragma_options_align_reset_failed : Warning<
"#pragma options align=reset failed: %0">,
InGroup;
diff --git a/clang/include/clang/Sema/Attr.h b/clang/include/clang/Sema/Attr.h
index 37c124ca7b454..3f0b10212789a 100644
--- a/clang/include/clang/Sema/Attr.h
+++ b/clang/include/clang/Sema/Attr.h
@@ -123,13 +123,6 @@ inline bool isInstanceMethod(const Decl *D) {
return false;
}
-inline bool checkIfMethodHasImplicitObjectParameter(const Decl *D) {
- if (const auto *MethodDecl = dyn_cast(D))
-return MethodDecl->isInstance() &&
- !MethodDecl->hasCXXExplicitFunctionObjectParameter();
- return false;
-}
-
/// Diagnose mutually exclusive attributes when present on a given
/// declaration. Returns true if diagnosed.
template
diff --git a/clang/include/clang/Sema/Sema.h b/clang/include/clang/Sema/Sema.h
index e30252749d2c3..6be6f6725e5b7 100644
--- a/clang/include/clang/Sema/Sema.h
+++ b/clang/include/clang/Sema/Sema.h
@@ -4594,10 +4594,6 @@ class Sema final : public SemaBase {
enum class RetainOwnershipKind { NS, CF, OS };
- void DiagnoseMissingFormatAttributes(Stmt *Body, const FunctionDecl *FDecl);
- std::vector
- GetMissingFormatAttributes(Stmt *Body, const FunctionDecl *FDecl);
-
UuidAttr *mergeUuidAttr(Decl *D, const AttributeCommonInfo &CI,
StringRef UuidAsWritten, MSGuidDecl *GuidDecl);
diff --git a/clang/lib/Sema/SemaDecl.cpp b/clang/lib/Sema/SemaDecl.cpp
index 0039df2a21bc6..80b5a8cd4bae6 100644
--- a/clang/lib/Sema/SemaDecl.cpp
+++ b/clang/lib/Sema/SemaDecl.cpp
@@ -15934,8 +15934,6 @@ Decl *Sema::ActOnFinishFunctionBody(Decl *dcl, Stmt
*Body,
}
}
- DiagnoseMissingFormatAttributes(Body, FD);
-
// We might not have found a prototype because we didn't wish to warn on
// the lack of a missing prototype. Try again without the checks for
// whether we want to warn on the missing prototype.
diff --git a/clang/lib/Sema/SemaDeclAttr.cpp b/clang/lib/Sema/SemaDeclAttr.cpp
index 5166e61bb41d4..f2cd46d1e7c93 100644
--- a/clang/lib/Sema
[llvm-branch-commits] [clang] [clang][OpenMP] Update validity check for reduction with `inscan` (PR #98500)
https://github.com/kparzysz updated
https://github.com/llvm/llvm-project/pull/98500
>From b58e4fae4b0c22c11e8a0d0e29b6f21c28d4da86 Mon Sep 17 00:00:00 2001
From: Krzysztof Parzyszek
Date: Thu, 11 Jul 2024 10:47:41 -0500
Subject: [PATCH] [clang][OpenMP] Update validity check for reduction with
`inscan`
Follow-up to 81cdf9472c (check for `scan` nesting). Also, it eliminates
the mentions of combined directives in `ActOnOpenMPReductionClause`.
---
clang/lib/Sema/SemaOpenMP.cpp | 24
1 file changed, 16 insertions(+), 8 deletions(-)
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 7ca89b0d4eb70..dc77a51b6569e 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -18603,14 +18603,22 @@ OMPClause *SemaOpenMP::ActOnOpenMPReductionClause(
// worksharing-loop construct, a worksharing-loop SIMD construct, a simd
// construct, a parallel worksharing-loop construct or a parallel
// worksharing-loop SIMD construct.
- if (Modifier == OMPC_REDUCTION_inscan &&
- (DSAStack->getCurrentDirective() != OMPD_for &&
- DSAStack->getCurrentDirective() != OMPD_for_simd &&
- DSAStack->getCurrentDirective() != OMPD_simd &&
- DSAStack->getCurrentDirective() != OMPD_parallel_for &&
- DSAStack->getCurrentDirective() != OMPD_parallel_for_simd)) {
-Diag(ModifierLoc, diag::err_omp_wrong_inscan_reduction);
-return nullptr;
+ // [5.2:136:1-4] A reduction clause with the inscan reduction-modifier may
+ // only appear on a worksharing-loop construct, a simd construct or a
+ // combined or composite construct for which any of the aforementioned
+ // constructs is a constituent construct and distribute is not a constituent
+ // construct.
+ if (Modifier == OMPC_REDUCTION_inscan) {
+SmallVector LeafOrComposite;
+ArrayRef CurrentLOC = getLeafOrCompositeConstructs(
+DSAStack->getCurrentDirective(), LeafOrComposite);
+bool Valid = llvm::any_of(CurrentLOC, [](OpenMPDirectiveKind DK) {
+ return llvm::is_contained({OMPD_for, OMPD_simd, OMPD_for_simd}, DK);
+});
+if (!Valid) {
+ Diag(ModifierLoc, diag::err_omp_wrong_inscan_reduction);
+ return nullptr;
+}
}
ReductionData RD(VarList.size(), Modifier);
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
https://github.com/kparzysz created
https://github.com/llvm/llvm-project/pull/98633
…lization`
Replace the explicit list of compound directives ending with taskloop with
checking for the last leaf construct.
>From 08ddba05e36c6c5b6fa5b4b158fbef21b77ab415 Mon Sep 17 00:00:00 2001
From: Krzysztof Parzyszek
Date: Thu, 11 Jul 2024 14:02:41 -0500
Subject: [PATCH] [clang][OpenMP] Simplify check for taskloop in
`ActOnOpenMPLoopInitialization`
Replace the explicit list of compound directives ending with taskloop
with checking for the last leaf construct.
---
clang/lib/Sema/SemaOpenMP.cpp | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 2340873c8fdd9..118cda253a437 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -9090,14 +9090,15 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
+ auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
+return getLeafConstructsOrSelf(DK).back() == OMPD_taskloop;
+ };
if (((isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != PredeterminedCKind && DVar.RefExpr &&
(getLangOpts().OpenMP <= 45 ||
(DVar.CKind != OMPC_lastprivate && DVar.CKind != OMPC_private)))
||
- ((isOpenMPWorksharingDirective(DKind) || DKind == OMPD_taskloop ||
- DKind == OMPD_master_taskloop || DKind == OMPD_masked_taskloop ||
- DKind == OMPD_parallel_master_taskloop ||
- DKind == OMPD_parallel_masked_taskloop ||
+ ((isOpenMPWorksharingDirective(DKind) ||
+ isOpenMPTaskloopDirective(DKind) ||
isOpenMPDistributeDirective(DKind)) &&
!isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != OMPC_private && DVar.CKind != OMPC_lastprivate)) &&
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
llvmbot wrote:
@llvm/pr-subscribers-clang
Author: Krzysztof Parzyszek (kparzysz)
Changes
…lization`
Replace the explicit list of compound directives ending with taskloop with
checking for the last leaf construct.
---
Full diff: https://github.com/llvm/llvm-project/pull/98633.diff
1 Files Affected:
- (modified) clang/lib/Sema/SemaOpenMP.cpp (+5-4)
``diff
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 2340873c8fdd9..118cda253a437 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -9090,14 +9090,15 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
+ auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
+return getLeafConstructsOrSelf(DK).back() == OMPD_taskloop;
+ };
if (((isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != PredeterminedCKind && DVar.RefExpr &&
(getLangOpts().OpenMP <= 45 ||
(DVar.CKind != OMPC_lastprivate && DVar.CKind != OMPC_private)))
||
- ((isOpenMPWorksharingDirective(DKind) || DKind == OMPD_taskloop ||
- DKind == OMPD_master_taskloop || DKind == OMPD_masked_taskloop ||
- DKind == OMPD_parallel_master_taskloop ||
- DKind == OMPD_parallel_masked_taskloop ||
+ ((isOpenMPWorksharingDirective(DKind) ||
+ isOpenMPTaskloopDirective(DKind) ||
isOpenMPDistributeDirective(DKind)) &&
!isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != OMPC_private && DVar.CKind != OMPC_lastprivate)) &&
``
https://github.com/llvm/llvm-project/pull/98633
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
@@ -9090,14 +9090,15 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
+ auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
alexey-bataev wrote:
IsOpenMPTaskloopDirective
https://github.com/llvm/llvm-project/pull/98633
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
https://github.com/kparzysz updated
https://github.com/llvm/llvm-project/pull/98633
>From 08ddba05e36c6c5b6fa5b4b158fbef21b77ab415 Mon Sep 17 00:00:00 2001
From: Krzysztof Parzyszek
Date: Thu, 11 Jul 2024 14:02:41 -0500
Subject: [PATCH 1/2] [clang][OpenMP] Simplify check for taskloop in
`ActOnOpenMPLoopInitialization`
Replace the explicit list of compound directives ending with taskloop
with checking for the last leaf construct.
---
clang/lib/Sema/SemaOpenMP.cpp | 9 +
1 file changed, 5 insertions(+), 4 deletions(-)
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 2340873c8fdd9..118cda253a437 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -9090,14 +9090,15 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
+ auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
+return getLeafConstructsOrSelf(DK).back() == OMPD_taskloop;
+ };
if (((isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != PredeterminedCKind && DVar.RefExpr &&
(getLangOpts().OpenMP <= 45 ||
(DVar.CKind != OMPC_lastprivate && DVar.CKind != OMPC_private)))
||
- ((isOpenMPWorksharingDirective(DKind) || DKind == OMPD_taskloop ||
- DKind == OMPD_master_taskloop || DKind == OMPD_masked_taskloop ||
- DKind == OMPD_parallel_master_taskloop ||
- DKind == OMPD_parallel_masked_taskloop ||
+ ((isOpenMPWorksharingDirective(DKind) ||
+ isOpenMPTaskloopDirective(DKind) ||
isOpenMPDistributeDirective(DKind)) &&
!isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != OMPC_private && DVar.CKind != OMPC_lastprivate)) &&
>From f38af28828a08daf3ba3a7f70104c38ccc6e4732 Mon Sep 17 00:00:00 2001
From: Krzysztof Parzyszek
Date: Fri, 12 Jul 2024 08:58:28 -0500
Subject: [PATCH 2/2] Capitalize IsOpenMPTaskloopDirective
---
clang/lib/Sema/SemaOpenMP.cpp | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/clang/lib/Sema/SemaOpenMP.cpp b/clang/lib/Sema/SemaOpenMP.cpp
index 118cda253a437..c1a58fc7f2076 100644
--- a/clang/lib/Sema/SemaOpenMP.cpp
+++ b/clang/lib/Sema/SemaOpenMP.cpp
@@ -9090,7 +9090,7 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
- auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
+ auto IsOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
return getLeafConstructsOrSelf(DK).back() == OMPD_taskloop;
};
if (((isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
@@ -9098,7 +9098,7 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
(getLangOpts().OpenMP <= 45 ||
(DVar.CKind != OMPC_lastprivate && DVar.CKind != OMPC_private)))
||
((isOpenMPWorksharingDirective(DKind) ||
- isOpenMPTaskloopDirective(DKind) ||
+ IsOpenMPTaskloopDirective(DKind) ||
isOpenMPDistributeDirective(DKind)) &&
!isOpenMPSimdDirective(DKind) && DVar.CKind != OMPC_unknown &&
DVar.CKind != OMPC_private && DVar.CKind != OMPC_lastprivate)) &&
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
@@ -9090,14 +9090,15 @@ void
SemaOpenMP::ActOnOpenMPLoopInitialization(SourceLocation ForLoc,
isOpenMPSimdDirective(DKind)
? (DSAStack->hasMutipleLoops() ? OMPC_lastprivate : OMPC_linear)
: OMPC_private;
+ auto isOpenMPTaskloopDirective = [](OpenMPDirectiveKind DK) {
kparzysz wrote:
Done
https://github.com/llvm/llvm-project/pull/98633
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][OpenMP] Simplify check for taskloop in `ActOnOpenMPLoopInitia… (PR #98633)
https://github.com/alexey-bataev approved this pull request. LG https://github.com/llvm/llvm-project/pull/98633 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [compiler-rt] [TySan] Fixed false positive when accessing offset member variables (PR #95387)
https://github.com/gbMattN updated
https://github.com/llvm/llvm-project/pull/95387
>From 8099113d68bd7c47c29f635bb10a048ddb99833b Mon Sep 17 00:00:00 2001
From: Matthew Nagy
Date: Fri, 28 Jun 2024 16:12:31 +
Subject: [PATCH] [TySan] Fixed false positive when accessing global object's
member variables
---
compiler-rt/lib/tysan/tysan.cpp | 19 +++-
.../test/tysan/global-struct-members.c| 31 +++
2 files changed, 49 insertions(+), 1 deletion(-)
create mode 100644 compiler-rt/test/tysan/global-struct-members.c
diff --git a/compiler-rt/lib/tysan/tysan.cpp b/compiler-rt/lib/tysan/tysan.cpp
index f627851d049e6..8235b0ec2b55e 100644
--- a/compiler-rt/lib/tysan/tysan.cpp
+++ b/compiler-rt/lib/tysan/tysan.cpp
@@ -221,7 +221,24 @@ __tysan_check(void *addr, int size, tysan_type_descriptor
*td, int flags) {
OldTDPtr -= i;
OldTD = *OldTDPtr;
-if (!isAliasingLegal(td, OldTD))
+// When shadow memory is set for global objects, the entire object is
tagged with the struct type
+// This means that when you access a member variable, tysan reads that as
you accessing a struct midway
+// through, with 'i' being the offset
+// Therefore, if you are accessing a struct, we need to find the member
type. We can go through the
+// members of the struct type and see if there is a member at the offset
you are accessing the struct by.
+// If there is indeed a member starting at offset 'i' in the struct, we
should check aliasing legality
+// with that type. If there isn't, we run alias checking on the struct
with will give us the correct error.
+tysan_type_descriptor *InternalMember = OldTD;
+if (OldTD->Tag == TYSAN_STRUCT_TD) {
+ for (int j = 0; j < OldTD->Struct.MemberCount; j++) {
+if (OldTD->Struct.Members[j].Offset == i) {
+ InternalMember = OldTD->Struct.Members[j].Type;
+ break;
+}
+ }
+}
+
+if (!isAliasingLegal(td, InternalMember))
reportError(addr, size, td, OldTD, AccessStr,
"accesses part of an existing object", -i, pc, bp, sp);
diff --git a/compiler-rt/test/tysan/global-struct-members.c
b/compiler-rt/test/tysan/global-struct-members.c
new file mode 100644
index 0..76ea3c431dd7b
--- /dev/null
+++ b/compiler-rt/test/tysan/global-struct-members.c
@@ -0,0 +1,31 @@
+// RUN: %clang_tysan -O0 %s -o %t && %run %t >%t.out 2>&1
+// RUN: FileCheck %s < %t.out
+
+#include
+
+struct X {
+ int a, b, c;
+} x;
+
+static struct X xArray[2];
+
+int main() {
+ x.a = 1;
+ x.b = 2;
+ x.c = 3;
+
+ printf("%d %d %d\n", x.a, x.b, x.c);
+ // CHECK-NOT: ERROR: TypeSanitizer: type-aliasing-violation
+
+ for (size_t i = 0; i < 2; i++) {
+xArray[i].a = 1;
+xArray[i].b = 1;
+xArray[i].c = 1;
+ }
+
+ struct X *xPtr = (struct X *)&(xArray[0].c);
+ xPtr->a = 1;
+ // CHECK: ERROR: TypeSanitizer: type-aliasing-violation
+ // CHECK: WRITE of size 4 at {{.*}} with type int (in X at offset 0)
accesses an existing object of type int (in X at offset 8)
+ // CHECK: {{#0 0x.* in main .*struct-members.c:}}[[@LINE-3]]
+}
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [compiler-rt] [TySan] Improved compatability for tests (PR #96507)
gbMattN wrote: @fhahn updated to remove merge conflicts https://github.com/llvm/llvm-project/pull/96507 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [libc] 6ea50a9 - Revert "[libc] Add erase function to blockstore (#97641)"
Author: Michael Jones
Date: 2024-07-12T10:50:56-07:00
New Revision: 6ea50a98e3f6db5c0fbd3ff6c16e2d9ac01fae37
URL:
https://github.com/llvm/llvm-project/commit/6ea50a98e3f6db5c0fbd3ff6c16e2d9ac01fae37
DIFF:
https://github.com/llvm/llvm-project/commit/6ea50a98e3f6db5c0fbd3ff6c16e2d9ac01fae37.diff
LOG: Revert "[libc] Add erase function to blockstore (#97641)"
This reverts commit 9e452c1af430e5090de92aebfe422abbf5e51ff3.
Added:
Modified:
libc/src/__support/blockstore.h
libc/test/src/__support/blockstore_test.cpp
Removed:
diff --git a/libc/src/__support/blockstore.h b/libc/src/__support/blockstore.h
index 41f5f196b7cef..8d13e0ed290df 100644
--- a/libc/src/__support/blockstore.h
+++ b/libc/src/__support/blockstore.h
@@ -9,11 +9,9 @@
#ifndef LLVM_LIBC_SRC___SUPPORT_BLOCKSTORE_H
#define LLVM_LIBC_SRC___SUPPORT_BLOCKSTORE_H
-#include "src/__support/CPP/array.h"
-#include "src/__support/CPP/new.h"
-#include "src/__support/CPP/type_traits.h"
-#include "src/__support/libc_assert.h"
#include "src/__support/macros/config.h"
+#include
+#include
#include
#include
@@ -100,16 +98,6 @@ class BlockStore {
return *reinterpret_cast(block->data + sizeof(T) * true_index);
}
-LIBC_INLINE Iterator operator+(int i) {
- LIBC_ASSERT(i >= 0 &&
- "BlockStore iterators only support incrementation.");
- auto other = *this;
- for (int j = 0; j < i; ++j)
-++other;
-
- return other;
-}
-
LIBC_INLINE bool operator==(const Iterator &rhs) const {
return block == rhs.block && index == rhs.index;
}
@@ -188,45 +176,6 @@ class BlockStore {
else
return Iterator(current, fill_count);
}
-
- // Removes the element at pos, then moves all the objects after back by one
to
- // fill the hole. It's assumed that pos is a valid iterator to somewhere in
- // this block_store.
- LIBC_INLINE void erase(Iterator pos) {
-const Iterator last_item = Iterator(current, fill_count);
-if (pos == last_item) {
- pop_back();
- return;
-}
-
-if constexpr (REVERSE_ORDER) {
- // REVERSE: Iterate from begin to pos
- const Iterator range_end = pos;
- Iterator cur = begin();
- T prev_val = *cur;
- ++cur;
- T cur_val = *cur;
-
- for (; cur != range_end; ++cur) {
-cur_val = *cur;
-*cur = prev_val;
-prev_val = cur_val;
- }
- // We will always need to move at least one item (since we know that pos
- // isn't the last item due to the check above).
- *cur = prev_val;
-} else {
- // FORWARD: Iterate from pos to end
- const Iterator range_end = end();
- Iterator cur = pos;
- Iterator prev = cur;
- ++cur;
-
- for (; cur != range_end; prev = cur, ++cur)
-*prev = *cur;
-}
-pop_back();
- }
};
template
diff --git a/libc/test/src/__support/blockstore_test.cpp
b/libc/test/src/__support/blockstore_test.cpp
index dd74ea18f2c02..5fe8fef1b6edc 100644
--- a/libc/test/src/__support/blockstore_test.cpp
+++ b/libc/test/src/__support/blockstore_test.cpp
@@ -64,99 +64,6 @@ class LlvmLibcBlockStoreTest : public
LIBC_NAMESPACE::testing::Test {
}
block_store.destroy(&block_store);
}
-
- template void erase_test() {
-using LIBC_NAMESPACE::BlockStore;
-BlockStore block_store;
-int i;
-
-constexpr int ARR_SIZE = 6;
-
-ASSERT_TRUE(block_store.empty());
-for (int i = 0; i < ARR_SIZE; i++) {
- ASSERT_TRUE(block_store.push_back(i + 1));
-}
-
-// block_store state should be {1,2,3,4,5,6}
-
-block_store.erase(block_store.begin());
-
-// FORWARD: block_store state should be {2,3,4,5,6}
-// REVERSE: block_store state should be {1,2,3,4,5}
-
-auto iter = block_store.begin();
-for (i = 0; iter != block_store.end(); ++i, ++iter) {
- if (!REVERSE) {
-ASSERT_EQ(*iter, i + 2);
- } else {
-ASSERT_EQ(*iter, (ARR_SIZE - 1) - i);
- }
-}
-
-// Assert that there were the correct number of elements
-ASSERT_EQ(i, ARR_SIZE - 1);
-
-block_store.erase(block_store.end());
-
-// BOTH: block_store state should be {2,3,4,5}
-
-iter = block_store.begin();
-for (i = 0; iter != block_store.end(); ++i, ++iter) {
- if (!REVERSE) {
-ASSERT_EQ(*iter, i + 2);
- } else {
-ASSERT_EQ(*iter, (ARR_SIZE - 1) - i);
- }
-}
-
-ASSERT_EQ(i, ARR_SIZE - 2);
-
-block_store.erase(block_store.begin() + 1);
-
-// FORWARD: block_store state should be {2,4,5}
-// REVERSE: block_store state should be {2,3,5}
-
-const int FORWARD_RESULTS[] = {2, 4, 5};
-const int REVERSE_RESULTS[] = {2, 3, 5};
-
-iter = block_store.begin();
-for (i = 0; iter != block_store.end(); ++i, ++iter) {
- if (!REVERSE) {
-ASSERT_EQ(*iter, FORWARD_RESULTS[i]);
- } else {
-ASSERT_EQ(*i
[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw for __builtin_amdgcn_global_atomic_fadd_{f32|f64} (PR #96872)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96872
>From e79b7f20e3a78de7c09c96e0b8f76132c9942a09 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Tue, 11 Jun 2024 10:58:44 +0200
Subject: [PATCH 1/2] clang/AMDGPU: Emit atomicrmw for
__builtin_amdgcn_global_atomic_fadd_{f32|f64}
Need to emit syncscope and new metadata to get the native instruction,
most of the time.
---
clang/lib/CodeGen/CGBuiltin.cpp | 39 +--
.../CodeGenOpenCL/builtins-amdgcn-gfx11.cl| 2 +-
.../builtins-fp-atomics-gfx12.cl | 4 +-
.../builtins-fp-atomics-gfx90a.cl | 4 +-
.../builtins-fp-atomics-gfx940.cl | 4 +-
5 files changed, 34 insertions(+), 19 deletions(-)
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 6cc0d9485720c..15d5e80fcd402 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -58,6 +58,7 @@
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/MatrixBuilder.h"
#include "llvm/IR/MemoryModelRelaxationAnnotations.h"
+#include "llvm/Support/AMDGPUAddrSpace.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/ScopedPrinter.h"
@@ -18658,8 +18659,6 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
Function *F = CGM.getIntrinsic(Intrin, { Src0->getType() });
return Builder.CreateCall(F, { Src0, Builder.getFalse() });
}
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
@@ -18671,18 +18670,11 @@ Value
*CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Intrinsic::ID IID;
llvm::Type *ArgTy = llvm::Type::getDoubleTy(getLLVMContext());
switch (BuiltinID) {
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
- ArgTy = llvm::Type::getFloatTy(getLLVMContext());
- IID = Intrinsic::amdgcn_global_atomic_fadd;
- break;
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
ArgTy = llvm::FixedVectorType::get(
llvm::Type::getHalfTy(getLLVMContext()), 2);
IID = Intrinsic::amdgcn_global_atomic_fadd;
break;
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
- IID = Intrinsic::amdgcn_global_atomic_fadd;
- break;
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
IID = Intrinsic::amdgcn_global_atomic_fmin;
break;
@@ -19097,7 +19089,9 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2bf16:
case AMDGPU::BI__builtin_amdgcn_ds_faddf:
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
- case AMDGPU::BI__builtin_amdgcn_ds_fmaxf: {
+ case AMDGPU::BI__builtin_amdgcn_ds_fmaxf:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64: {
llvm::AtomicRMWInst::BinOp BinOp;
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
@@ -19113,6 +19107,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2bf16:
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
BinOp = llvm::AtomicRMWInst::FAdd;
break;
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
@@ -19147,8 +19143,13 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
ProcessOrderScopeAMDGCN(EmitScalarExpr(E->getArg(2)),
EmitScalarExpr(E->getArg(3)), AO, SSID);
} else {
- // The ds_atomic_fadd_* builtins do not have syncscope/order arguments.
- SSID = llvm::SyncScope::System;
+ // Most of the builtins do not have syncscope/order arguments. For DS
+ // atomics the scope doesn't really matter, as they implicitly operate at
+ // workgroup scope.
+ //
+ // The global/flat cases need to use agent scope to consistently produce
+ // the native instruction instead of a cmpxchg expansion.
+ SSID = getLLVMContext().getOrInsertSyncScopeID("agent");
AO = AtomicOrdering::SequentiallyConsistent;
// The v2bf16 builtin uses i16 instead of a natural bfloat type.
@@ -19163,6 +19164,20 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
Builder.CreateAtomicRMW(BinOp, Ptr, Val, AO, SSID);
if (Volatile)
RMW->setVolatile(true);
+
+unsigned AddrSpace = Ptr.getType()->getAddressSpace();
+if (AddrSpace != llvm::AMDGPUAS::LOCAL_ADDRESS) {
+ // Most targets require "amdgpu.no.fine.grained.memory" to emit the
nativ
[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw from {global|flat}_atomic_fadd_v2f16 builtins (PR #96873)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96873
>From 9a6ec14c6e2acdae6c5c5a50a0f1fd4847f4cd9a Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:12:59 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from
{global|flat}_atomic_fadd_v2f16 builtins
---
clang/lib/CodeGen/CGBuiltin.cpp | 20 ++-
.../builtins-fp-atomics-gfx12.cl | 9 ++---
.../builtins-fp-atomics-gfx90a.cl | 2 +-
.../builtins-fp-atomics-gfx940.cl | 3 ++-
4 files changed, 15 insertions(+), 19 deletions(-)
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 3cf708da269b3..105566b584108 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -18659,22 +18659,15 @@ Value
*CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
Function *F = CGM.getIntrinsic(Intrin, { Src0->getType() });
return Builder.CreateCall(F, { Src0, Builder.getFalse() });
}
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16: {
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32: {
Intrinsic::ID IID;
llvm::Type *ArgTy = llvm::Type::getDoubleTy(getLLVMContext());
switch (BuiltinID) {
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
- ArgTy = llvm::FixedVectorType::get(
- llvm::Type::getHalfTy(getLLVMContext()), 2);
- IID = Intrinsic::amdgcn_global_atomic_fadd;
- break;
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
IID = Intrinsic::amdgcn_global_atomic_fmin;
break;
@@ -18694,11 +18687,6 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
ArgTy = llvm::Type::getFloatTy(getLLVMContext());
IID = Intrinsic::amdgcn_flat_atomic_fadd;
break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
- ArgTy = llvm::FixedVectorType::get(
- llvm::Type::getHalfTy(getLLVMContext()), 2);
- IID = Intrinsic::amdgcn_flat_atomic_fadd;
- break;
}
llvm::Value *Addr = EmitScalarExpr(E->getArg(0));
llvm::Value *Val = EmitScalarExpr(E->getArg(1));
@@ -19091,7 +19079,9 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
case AMDGPU::BI__builtin_amdgcn_ds_fmaxf:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64: {
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16: {
llvm::AtomicRMWInst::BinOp BinOp;
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
@@ -19109,6 +19099,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2bf16:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
BinOp = llvm::AtomicRMWInst::FAdd;
break;
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
diff --git a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
index 6b8a6d14575db..07e63a8711c7f 100644
--- a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
+++ b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
@@ -48,7 +48,8 @@ void test_local_add_2f16_noret(__local half2 *addr, half2 x) {
}
// CHECK-LABEL: test_flat_add_2f16
-// CHECK: call <2 x half> @llvm.amdgcn.flat.atomic.fadd.v2f16.p0.v2f16(ptr
%{{.*}}, <2 x half> %{{.*}})
+// CHECK: [[RMW:%.+]] = atomicrmw fadd ptr %{{.+}}, <2 x half> %{{.+}}
syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !{{[0-9]+$}}
+
// GFX12-LABEL: test_flat_add_2f16
// GFX12: flat_atomic_pk_add_f16
half2 test_flat_add_2f16(__generic half2 *addr, half2 x) {
@@ -64,7 +65,8 @@ short2 test_flat_add_2bf16(__generic short2 *addr, short2 x) {
}
// CHECK-LABEL: test_global_add_half2
-// CHECK: call <2 x half> @llvm.amdgcn.global.atomic.fadd.v2f16.p1.v2f16(ptr
addrspace(1) %{{.*}}, <2 x half> %{{.*}})
+// CHECK: [[RMW:%.+]] = atomicrmw fadd ptr addrspace(1) %{{.+}}, <2 x half>
%{{.+}} syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory
!{{[0-9]+$}}
+
// GFX12-LABEL: test_global_add_half2
// GFX12: global_atomic_pk_add_f16 v2, v[0:1], v2, off
[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw from flat_atomic_{f32|f64} builtins (PR #96874)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96874
>From f124301ced6c21ab35a3af57c839e32e6b3ec269 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:15:26 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw from flat_atomic_{f32|f64}
builtins
---
clang/lib/CodeGen/CGBuiltin.cpp | 17 ++---
.../CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl | 6 --
.../CodeGenOpenCL/builtins-fp-atomics-gfx940.cl | 3 ++-
3 files changed, 12 insertions(+), 14 deletions(-)
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 105566b584108..91702246c9571 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -18661,10 +18661,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
}
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32: {
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64: {
Intrinsic::ID IID;
llvm::Type *ArgTy = llvm::Type::getDoubleTy(getLLVMContext());
switch (BuiltinID) {
@@ -18674,19 +18672,12 @@ Value
*CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
IID = Intrinsic::amdgcn_global_atomic_fmax;
break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
- IID = Intrinsic::amdgcn_flat_atomic_fadd;
- break;
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
IID = Intrinsic::amdgcn_flat_atomic_fmin;
break;
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64:
IID = Intrinsic::amdgcn_flat_atomic_fmax;
break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
- ArgTy = llvm::Type::getFloatTy(getLLVMContext());
- IID = Intrinsic::amdgcn_flat_atomic_fadd;
- break;
}
llvm::Value *Addr = EmitScalarExpr(E->getArg(0));
llvm::Value *Val = EmitScalarExpr(E->getArg(1));
@@ -19081,7 +19072,9 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16: {
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64: {
llvm::AtomicRMWInst::BinOp BinOp;
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
@@ -19101,6 +19094,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
BinOp = llvm::AtomicRMWInst::FAdd;
break;
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
diff --git a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
index cd10777dbe079..02e289427238f 100644
--- a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
+++ b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
@@ -45,7 +45,8 @@ void test_global_max_f64(__global double *addr, double x){
}
// CHECK-LABEL: test_flat_add_local_f64
-// CHECK: call double @llvm.amdgcn.flat.atomic.fadd.f64.p3.f64(ptr
addrspace(3) %{{.*}}, double %{{.*}})
+// CHECK: = atomicrmw fadd ptr addrspace(3) %{{.+}}, double %{{.+}}
syncscope("agent") seq_cst, align 8{{$}}
+
// GFX90A-LABEL: test_flat_add_local_f64$local
// GFX90A: ds_add_rtn_f64
void test_flat_add_local_f64(__local double *addr, double x){
@@ -54,7 +55,8 @@ void test_flat_add_local_f64(__local double *addr, double x){
}
// CHECK-LABEL: test_flat_global_add_f64
-// CHECK: call double @llvm.amdgcn.flat.atomic.fadd.f64.p1.f64(ptr
addrspace(1) %{{.*}}, double %{{.*}})
+// CHECK: = atomicrmw fadd ptr addrspace(1) {{.+}}, double %{{.+}}
syncscope("agent") seq_cst, align 8, !amdgpu.no.fine.grained.memory !{{[0-9]+$}}
+
// GFX90A-LABEL: test_flat_global_add_f64$local
// GFX90A: global_atomic_add_f64
void test_flat_global_add_f64(__global double *addr, double x){
diff --git a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx940.cl
b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx940.cl
index 589dcd406630d..bd9b8c7268e06 100644
--- a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx940.cl
+++ b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx940.cl
@@ -10,7 +10,8 @@ typedef half _
[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw for global/flat fadd v2bf16 builtins (PR #96875)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96875
>From fc87b903a7007710f97eae4b99b6d518c0ad5c81 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 19:34:43 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for global/flat fadd v2bf16
builtins
---
clang/lib/CodeGen/CGBuiltin.cpp | 26 ++-
.../builtins-fp-atomics-gfx12.cl | 24 -
.../builtins-fp-atomics-gfx90a.cl | 6 ++---
.../builtins-fp-atomics-gfx940.cl | 14 +++---
4 files changed, 38 insertions(+), 32 deletions(-)
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 91702246c9571..6c97b1d1108a5 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -18685,22 +18685,6 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
CGM.getIntrinsic(IID, {ArgTy, Addr->getType(), Val->getType()});
return Builder.CreateCall(F, {Addr, Val});
}
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16: {
-Intrinsic::ID IID;
-switch (BuiltinID) {
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16:
- IID = Intrinsic::amdgcn_global_atomic_fadd_v2bf16;
- break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16:
- IID = Intrinsic::amdgcn_flat_atomic_fadd_v2bf16;
- break;
-}
-llvm::Value *Addr = EmitScalarExpr(E->getArg(0));
-llvm::Value *Val = EmitScalarExpr(E->getArg(1));
-llvm::Function *F = CGM.getIntrinsic(IID, {Addr->getType()});
-return Builder.CreateCall(F, {Addr, Val});
- }
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b64_i32:
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b64_v2i32:
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b128_v4i16:
@@ -19074,7 +19058,9 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64: {
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16: {
llvm::AtomicRMWInst::BinOp BinOp;
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
@@ -19096,6 +19082,8 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2f16:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16:
BinOp = llvm::AtomicRMWInst::FAdd;
break;
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
@@ -19140,7 +19128,9 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
AO = AtomicOrdering::Monotonic;
// The v2bf16 builtin uses i16 instead of a natural bfloat type.
- if (BuiltinID == AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2bf16) {
+ if (BuiltinID == AMDGPU::BI__builtin_amdgcn_ds_atomic_fadd_v2bf16 ||
+ BuiltinID == AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16 ||
+ BuiltinID == AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16) {
llvm::Type *V2BF16Ty = FixedVectorType::get(
llvm::Type::getBFloatTy(Builder.getContext()), 2);
Val = Builder.CreateBitCast(Val, V2BF16Ty);
diff --git a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
index 07e63a8711c7f..e8b6eb57c38d7 100644
--- a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
+++ b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx12.cl
@@ -11,7 +11,7 @@ typedef short __attribute__((ext_vector_type(2))) short2;
// CHECK-LABEL: test_local_add_2bf16
// CHECK: [[BC0:%.+]] = bitcast <2 x i16> {{.+}} to <2 x bfloat>
-// CHECK: [[RMW:%.+]] = atomicrmw fadd ptr addrspace(3) %{{.+}}, <2 x bfloat>
[[BC0]] syncscope("agent") monotonic, align 4
+// CHECK-NEXT: [[RMW:%.+]] = atomicrmw fadd ptr addrspace(3) %{{.+}}, <2 x
bfloat> [[BC0]] syncscope("agent") monotonic, align 4
// CHECK-NEXT: bitcast <2 x bfloat> [[RMW]] to <2 x i16>
// GFX12-LABEL: test_local_add_2bf16
@@ -48,7 +48,7 @@ void test_local_add_2f16_noret(__local half2 *addr, half2 x) {
}
// CHECK-LABEL: test_flat_add_2f16
-// CHECK: [[RMW:%.+]] = atomicrmw fadd ptr %{{.+}}, <2 x half> %{{.+}}
syncscope("agent") seq_cst, align 4, !amdgpu.no.fine.grained.memory !{{[0-9]+$}}
+// CHECK: [[RMW:%.+]] = atomicrmw fadd ptr %{{.+}}, <2 x half> %{{.+}}
syncscope("agent") monotonic, align 4, !amdgpu.no.fine.grained.memory
!{{[0-9]+$}}
// GFX12-LABEL: test_flat_add_2f
[llvm-branch-commits] [clang] clang/AMDGPU: Emit atomicrmw for flat/global atomic min/max f64 builtins (PR #96876)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/96876
>From e0715016475eaaff55ef7143ea148c4a47e7f825 Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Wed, 26 Jun 2024 23:18:32 +0200
Subject: [PATCH] clang/AMDGPU: Emit atomicrmw for flat/global atomic min/max
f64 builtins
---
clang/lib/CodeGen/CGBuiltin.cpp | 36 +--
.../builtins-fp-atomics-gfx90a.cl | 18 ++
2 files changed, 21 insertions(+), 33 deletions(-)
diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp
index 6c97b1d1108a5..42d57671f9c76 100644
--- a/clang/lib/CodeGen/CGBuiltin.cpp
+++ b/clang/lib/CodeGen/CGBuiltin.cpp
@@ -18659,32 +18659,6 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
Function *F = CGM.getIntrinsic(Intrin, { Src0->getType() });
return Builder.CreateCall(F, { Src0, Builder.getFalse() });
}
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
- case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64: {
-Intrinsic::ID IID;
-llvm::Type *ArgTy = llvm::Type::getDoubleTy(getLLVMContext());
-switch (BuiltinID) {
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
- IID = Intrinsic::amdgcn_global_atomic_fmin;
- break;
-case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
- IID = Intrinsic::amdgcn_global_atomic_fmax;
- break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
- IID = Intrinsic::amdgcn_flat_atomic_fmin;
- break;
-case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64:
- IID = Intrinsic::amdgcn_flat_atomic_fmax;
- break;
-}
-llvm::Value *Addr = EmitScalarExpr(E->getArg(0));
-llvm::Value *Val = EmitScalarExpr(E->getArg(1));
-llvm::Function *F =
-CGM.getIntrinsic(IID, {ArgTy, Addr->getType(), Val->getType()});
-return Builder.CreateCall(F, {Addr, Val});
- }
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b64_i32:
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b64_v2i32:
case AMDGPU::BI__builtin_amdgcn_global_load_tr_b128_v4i16:
@@ -19060,7 +19034,11 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f32:
case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_f64:
case AMDGPU::BI__builtin_amdgcn_global_atomic_fadd_v2bf16:
- case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16: {
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fadd_v2bf16:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
+ case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
+ case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64: {
llvm::AtomicRMWInst::BinOp BinOp;
switch (BuiltinID) {
case AMDGPU::BI__builtin_amdgcn_atomic_inc32:
@@ -19087,8 +19065,12 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
BinOp = llvm::AtomicRMWInst::FAdd;
break;
case AMDGPU::BI__builtin_amdgcn_ds_fminf:
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fmin_f64:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmin_f64:
BinOp = llvm::AtomicRMWInst::FMin;
break;
+case AMDGPU::BI__builtin_amdgcn_global_atomic_fmax_f64:
+case AMDGPU::BI__builtin_amdgcn_flat_atomic_fmax_f64:
case AMDGPU::BI__builtin_amdgcn_ds_fmaxf:
BinOp = llvm::AtomicRMWInst::FMax;
break;
diff --git a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
index 9381ce951df3e..556e553903d1a 100644
--- a/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
+++ b/clang/test/CodeGenOpenCL/builtins-fp-atomics-gfx90a.cl
@@ -27,7 +27,8 @@ void test_global_add_half2(__global half2 *addr, half2 x) {
}
// CHECK-LABEL: test_global_global_min_f64
-// CHECK: call double @llvm.amdgcn.global.atomic.fmin.f64.p1.f64(ptr
addrspace(1) %{{.*}}, double %{{.*}})
+// CHECK: = atomicrmw fmin ptr addrspace(1) {{.+}}, double %{{.+}}
syncscope("agent") monotonic, align 8, !amdgpu.no.fine.grained.memory
!{{[0-9]+$}}
+
// GFX90A-LABEL: test_global_global_min_f64$local
// GFX90A: global_atomic_min_f64
void test_global_global_min_f64(__global double *addr, double x){
@@ -36,7 +37,8 @@ void test_global_global_min_f64(__global double *addr, double
x){
}
// CHECK-LABEL: test_global_max_f64
-// CHECK: call double @llvm.amdgcn.global.atomic.fmax.f64.p1.f64(ptr
addrspace(1) %{{.*}}, double %{{.*}})
+// CHECK: = atomicrmw fmax ptr addrspace(1) {{.+}}, double %{{.+}}
syncscope("agent") monotonic, align 8, !amdgpu.no.fine.grained.memory
!{{[0-9]+$}}
+
// GFX90A-LABEL: test_global_max_f64$local
// GFX90A: global_atomic_max_f64
void test_global_max_f64(__global double *addr, double x){
@@ -65,7 +67,8 @@ void test_flat_global_add_f64(__global double *addr, doub
[llvm-branch-commits] [llvm] AMDGPU: Remove flat/global atomic fadd v2bf16 intrinsics (PR #97050)
https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/97050
>From f708d5e78f8ac415c2dce8057304f13bf3236b2b Mon Sep 17 00:00:00 2001
From: Matt Arsenault
Date: Thu, 27 Jun 2024 16:32:48 +0200
Subject: [PATCH] AMDGPU: Remove flat/global atomic fadd v2bf16 intrinsics
These are now fully covered by atomicrmw.
---
llvm/include/llvm/IR/IntrinsicsAMDGPU.td | 4 -
llvm/lib/IR/AutoUpgrade.cpp | 14 +-
llvm/lib/Target/AMDGPU/AMDGPUInstructions.td | 2 -
.../Target/AMDGPU/AMDGPURegisterBankInfo.cpp | 2 -
.../Target/AMDGPU/AMDGPUSearchableTables.td | 2 -
llvm/lib/Target/AMDGPU/FLATInstructions.td| 2 -
llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 6 +-
llvm/test/Bitcode/amdgcn-atomic.ll| 22 ++
.../AMDGPU/GlobalISel/fp-atomics-gfx940.ll| 54 -
.../test/CodeGen/AMDGPU/fp-atomics-gfx1200.ll | 100 -
llvm/test/CodeGen/AMDGPU/fp-atomics-gfx940.ll | 193 --
11 files changed, 33 insertions(+), 368 deletions(-)
diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
index 71b1e832bde3c..9cf4d6352d23d 100644
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2907,10 +2907,6 @@ multiclass AMDGPUMFp8SmfmacIntrinsic {
def NAME#"_"#kind : AMDGPUMFp8SmfmacIntrinsic;
}
-// bf16 atomics use v2i16 argument since there is no bf16 data type in the
llvm.
-def int_amdgcn_global_atomic_fadd_v2bf16 : AMDGPUAtomicRtn;
-def int_amdgcn_flat_atomic_fadd_v2bf16 : AMDGPUAtomicRtn;
-
defset list AMDGPUMFMAIntrinsics940 = {
def int_amdgcn_mfma_i32_16x16x32_i8 : AMDGPUMfmaIntrinsic;
def int_amdgcn_mfma_i32_32x32x16_i8 : AMDGPUMfmaIntrinsic;
diff --git a/llvm/lib/IR/AutoUpgrade.cpp b/llvm/lib/IR/AutoUpgrade.cpp
index 53de9eef516b3..f566a0e3c3043 100644
--- a/llvm/lib/IR/AutoUpgrade.cpp
+++ b/llvm/lib/IR/AutoUpgrade.cpp
@@ -1034,7 +1034,9 @@ static bool upgradeIntrinsicFunction1(Function *F,
Function *&NewFn,
}
if (Name.starts_with("ds.fadd") || Name.starts_with("ds.fmin") ||
- Name.starts_with("ds.fmax")) {
+ Name.starts_with("ds.fmax") ||
+ Name.starts_with("global.atomic.fadd.v2bf16") ||
+ Name.starts_with("flat.atomic.fadd.v2bf16")) {
// Replaced with atomicrmw fadd/fmin/fmax, so there's no new
// declaration.
NewFn = nullptr;
@@ -4042,7 +4044,9 @@ static Value *upgradeAMDGCNIntrinsicCall(StringRef Name,
CallBase *CI,
.StartsWith("ds.fmin", AtomicRMWInst::FMin)
.StartsWith("ds.fmax", AtomicRMWInst::FMax)
.StartsWith("atomic.inc.", AtomicRMWInst::UIncWrap)
- .StartsWith("atomic.dec.", AtomicRMWInst::UDecWrap);
+ .StartsWith("atomic.dec.", AtomicRMWInst::UDecWrap)
+ .StartsWith("global.atomic.fadd", AtomicRMWInst::FAdd)
+ .StartsWith("flat.atomic.fadd", AtomicRMWInst::FAdd);
unsigned NumOperands = CI->getNumOperands();
if (NumOperands < 3) // Malformed bitcode.
@@ -4097,8 +4101,10 @@ static Value *upgradeAMDGCNIntrinsicCall(StringRef Name,
CallBase *CI,
Builder.CreateAtomicRMW(RMWOp, Ptr, Val, std::nullopt, Order, SSID);
if (PtrTy->getAddressSpace() != 3) {
-RMW->setMetadata("amdgpu.no.fine.grained.memory",
- MDNode::get(F->getContext(), {}));
+MDNode *EmptyMD = MDNode::get(F->getContext(), {});
+RMW->setMetadata("amdgpu.no.fine.grained.memory", EmptyMD);
+if (RMWOp == AtomicRMWInst::FAdd && RetTy->isFloatTy())
+ RMW->setMetadata("amdgpu.ignore.denormal.mode", EmptyMD);
}
if (IsVolatile)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
index c6dbc58395e48..db8b44149cf47 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
@@ -620,12 +620,10 @@ multiclass local_addr_space_atomic_op {
defm int_amdgcn_flat_atomic_fadd : noret_op;
defm int_amdgcn_flat_atomic_fadd : flat_addr_space_atomic_op;
-defm int_amdgcn_flat_atomic_fadd_v2bf16 : noret_op;
defm int_amdgcn_flat_atomic_fmin : noret_op;
defm int_amdgcn_flat_atomic_fmax : noret_op;
defm int_amdgcn_global_atomic_fadd : global_addr_space_atomic_op;
defm int_amdgcn_flat_atomic_fadd : global_addr_space_atomic_op;
-defm int_amdgcn_global_atomic_fadd_v2bf16 : noret_op;
defm int_amdgcn_global_atomic_fmin : noret_op;
defm int_amdgcn_global_atomic_fmax : noret_op;
defm int_amdgcn_global_atomic_csub : noret_op;
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
index 9e7694f41d6b8..74686cd10512c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -4897,8 +4897,6 @@ AMDGPURegisterBankInfo::getInstrMapping(const
MachineInstr &MI) const {
case Intrinsic::amdgcn_flat_atomic_fmax:
case Intrinsic::amdgcn_fl
[llvm-branch-commits] [clang] [clang][test] remove unused `run` overload in `BoundNodesCallback` (PR #94244)
https://github.com/5chmidti updated
https://github.com/llvm/llvm-project/pull/94244
>From 51de6278688635cdcd5a8dd73a2ef0ede2a31b37 Mon Sep 17 00:00:00 2001
From: Julian Schmidt
Date: Sat, 1 Jun 2024 17:49:13 +0200
Subject: [PATCH] [clang][test] remove unused `run` overload in
`BoundNodesCallback`
The overload that did not take the additional `ASTContext *` argument is
unnecessary when the context could simply be commented out, as it is
always passed to `run` from `VerifyMatcher::run`.
This patch removes the single-argument overload in favor of having a
single overload.
---
clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp | 2 --
clang/unittests/ASTMatchers/ASTMatchersTest.h| 7 +--
clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp | 9 +++--
3 files changed, 4 insertions(+), 14 deletions(-)
diff --git a/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
b/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
index 3295ad1e21455..ebf548eb25431 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
+++ b/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
@@ -2030,8 +2030,6 @@ TEST_P(ASTMatchersTest,
template
class VerifyAncestorHasChildIsEqual : public BoundNodesCallback {
public:
- bool run(const BoundNodes *Nodes) override { return false; }
-
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const T *Node = Nodes->getNodeAs("");
return verify(*Nodes, *Context, Node);
diff --git a/clang/unittests/ASTMatchers/ASTMatchersTest.h
b/clang/unittests/ASTMatchers/ASTMatchersTest.h
index e981299531574..ad2f5f355621c 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersTest.h
+++ b/clang/unittests/ASTMatchers/ASTMatchersTest.h
@@ -28,7 +28,6 @@ using clang::tooling::runToolOnCodeWithArgs;
class BoundNodesCallback {
public:
virtual ~BoundNodesCallback() {}
- virtual bool run(const BoundNodes *BoundNodes) = 0;
virtual bool run(const BoundNodes *BoundNodes, ASTContext *Context) = 0;
virtual void onEndOfTranslationUnit() {}
};
@@ -403,7 +402,7 @@ template class VerifyIdIsBoundTo : public
BoundNodesCallback {
EXPECT_EQ("", Name);
}
- bool run(const BoundNodes *Nodes) override {
+ bool run(const BoundNodes *Nodes, ASTContext * /*Context*/) override {
const BoundNodes::IDToNodeMap &M = Nodes->getMap();
if (Nodes->getNodeAs(Id)) {
++Count;
@@ -426,10 +425,6 @@ template class VerifyIdIsBoundTo : public
BoundNodesCallback {
return false;
}
- bool run(const BoundNodes *Nodes, ASTContext *Context) override {
-return run(Nodes);
- }
-
private:
const std::string Id;
const int ExpectedCount;
diff --git a/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
b/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
index 3c033638960de..97355d22dd72b 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
+++ b/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
@@ -5641,7 +5641,6 @@ TEST(HasParent, MatchesAllParents) {
TEST(HasParent, NoDuplicateParents) {
class HasDuplicateParents : public BoundNodesCallback {
public:
-bool run(const BoundNodes *Nodes) override { return false; }
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const Stmt *Node = Nodes->getNodeAs("node");
std::set Parents;
@@ -5850,16 +5849,14 @@ template class VerifyMatchOnNode : public
BoundNodesCallback {
public:
VerifyMatchOnNode(StringRef Id, const internal::Matcher &InnerMatcher,
StringRef InnerId)
-: Id(Id), InnerMatcher(InnerMatcher), InnerId(InnerId) {
- }
-
- bool run(const BoundNodes *Nodes) override { return false; }
+ : Id(Id), InnerMatcher(InnerMatcher), InnerId(InnerId) {}
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const T *Node = Nodes->getNodeAs(Id);
return selectFirst(InnerId, match(InnerMatcher, *Node, *Context)) !=
- nullptr;
+ nullptr;
}
+
private:
std::string Id;
internal::Matcher InnerMatcher;
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][test] remove unused `run` overload in `BoundNodesCallback` (PR #94244)
5chmidti wrote: rebase on trunk + rebased stack https://github.com/llvm/llvm-project/pull/94244 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][test] add testing for the AST matcher reference (PR #94248)
5chmidti wrote: rebase on trunk + rebased stack https://github.com/llvm/llvm-project/pull/94248 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
[llvm-branch-commits] [clang] [clang][test] remove unused `run` overload in `BoundNodesCallback` (PR #94244)
https://github.com/5chmidti updated
https://github.com/llvm/llvm-project/pull/94244
>From 26d5b0377af3df4c551ae16d053684bb8c75e233 Mon Sep 17 00:00:00 2001
From: Julian Schmidt
Date: Sat, 1 Jun 2024 17:49:13 +0200
Subject: [PATCH] [clang][test] remove unused `run` overload in
`BoundNodesCallback`
The overload that did not take the additional `ASTContext *` argument is
unnecessary when the context could simply be commented out, as it is
always passed to `run` from `VerifyMatcher::run`.
This patch removes the single-argument overload in favor of having a
single overload.
---
.../unittests/ASTMatchers/ASTMatchersNodeTest.cpp | 2 --
clang/unittests/ASTMatchers/ASTMatchersTest.h | 7 +--
.../ASTMatchers/ASTMatchersTraversalTest.cpp | 15 ---
3 files changed, 5 insertions(+), 19 deletions(-)
diff --git a/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
b/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
index 3295ad1e2145..ebf548eb2543 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
+++ b/clang/unittests/ASTMatchers/ASTMatchersNodeTest.cpp
@@ -2030,8 +2030,6 @@ TEST_P(ASTMatchersTest,
template
class VerifyAncestorHasChildIsEqual : public BoundNodesCallback {
public:
- bool run(const BoundNodes *Nodes) override { return false; }
-
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const T *Node = Nodes->getNodeAs("");
return verify(*Nodes, *Context, Node);
diff --git a/clang/unittests/ASTMatchers/ASTMatchersTest.h
b/clang/unittests/ASTMatchers/ASTMatchersTest.h
index e98129953157..ad2f5f355621 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersTest.h
+++ b/clang/unittests/ASTMatchers/ASTMatchersTest.h
@@ -28,7 +28,6 @@ using clang::tooling::runToolOnCodeWithArgs;
class BoundNodesCallback {
public:
virtual ~BoundNodesCallback() {}
- virtual bool run(const BoundNodes *BoundNodes) = 0;
virtual bool run(const BoundNodes *BoundNodes, ASTContext *Context) = 0;
virtual void onEndOfTranslationUnit() {}
};
@@ -403,7 +402,7 @@ template class VerifyIdIsBoundTo : public
BoundNodesCallback {
EXPECT_EQ("", Name);
}
- bool run(const BoundNodes *Nodes) override {
+ bool run(const BoundNodes *Nodes, ASTContext * /*Context*/) override {
const BoundNodes::IDToNodeMap &M = Nodes->getMap();
if (Nodes->getNodeAs(Id)) {
++Count;
@@ -426,10 +425,6 @@ template class VerifyIdIsBoundTo : public
BoundNodesCallback {
return false;
}
- bool run(const BoundNodes *Nodes, ASTContext *Context) override {
-return run(Nodes);
- }
-
private:
const std::string Id;
const int ExpectedCount;
diff --git a/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
b/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
index 3c033638960d..d887c5ba8f05 100644
--- a/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
+++ b/clang/unittests/ASTMatchers/ASTMatchersTraversalTest.cpp
@@ -5641,7 +5641,6 @@ TEST(HasParent, MatchesAllParents) {
TEST(HasParent, NoDuplicateParents) {
class HasDuplicateParents : public BoundNodesCallback {
public:
-bool run(const BoundNodes *Nodes) override { return false; }
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const Stmt *Node = Nodes->getNodeAs("node");
std::set Parents;
@@ -5850,16 +5849,14 @@ template class VerifyMatchOnNode : public
BoundNodesCallback {
public:
VerifyMatchOnNode(StringRef Id, const internal::Matcher &InnerMatcher,
StringRef InnerId)
-: Id(Id), InnerMatcher(InnerMatcher), InnerId(InnerId) {
- }
-
- bool run(const BoundNodes *Nodes) override { return false; }
+ : Id(Id), InnerMatcher(InnerMatcher), InnerId(InnerId) {}
bool run(const BoundNodes *Nodes, ASTContext *Context) override {
const T *Node = Nodes->getNodeAs(Id);
return selectFirst(InnerId, match(InnerMatcher, *Node, *Context)) !=
- nullptr;
+ nullptr;
}
+
private:
std::string Id;
internal::Matcher InnerMatcher;
@@ -6053,7 +6050,7 @@ namespace {
class ForCallablePreservesBindingWithMultipleParentsTestCallback
: public BoundNodesCallback {
public:
- bool run(const BoundNodes *BoundNodes) override {
+ bool run(const BoundNodes *BoundNodes, ASTContext *Context) override {
FunctionDecl const *FunDecl =
BoundNodes->getNodeAs("funDecl");
// Validate test assumptions. This would be expressed as ASSERT_* in
@@ -6090,10 +6087,6 @@ class
ForCallablePreservesBindingWithMultipleParentsTestCallback
return true;
}
- bool run(const BoundNodes *BoundNodes, ASTContext *Context) override {
-return run(BoundNodes);
- }
-
private:
void ExpectCorrectResult(StringRef LogInfo,
ArrayRef Results) const {
___
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
