Codegen support for reduction over private variable with reduction
clause. Section 7.6.10 in in OpenMP 6.0 spec.
- An internal shared copy is initialized with an initializer value.
- The shared copy is updated by combining its value with the values from
the private copies created by the clause.
- Once an encountering thread verifies that all updates are complete,
its original list item is updated by merging its value with that of the
shared copy and then broadcast to all threads.
Sample Test Case from OpenMP 6.0 Example
```
#include <assert.h>
#include <omp.h>
#define N 10
void do_red(int n, int *v, int &sum_v)
{
sum_v = 0; // sum_v is private
#pragma omp for reduction(original(private),+: sum_v)
for (int i = 0; i < n; i++)
{
sum_v += v[i];
}
}
int main(void)
{
int v[N];
for (int i = 0; i < N; i++)
v[i] = i;
#pragma omp parallel num_threads(4)
{
int s_v; // s_v is private
do_red(N, v, s_v);
assert(s_v == 45);
}
return 0;
}
```
Expected Codegen:
```
// A shared global/static variable is introduced for the reduction result.
// This variable is initialized (e.g., using memset or a UDR initializer)
// e.g., .omp.reduction.internal_private_var
// Barrier before any thread performs combination
call void @__kmpc_barrier(...)
// Initialization block (executed by thread 0)
// e.g., call void @llvm.memset.p0.i64(...) or call @udr_initializer(...)
call void @__kmpc_critical(...)
// Inside critical section:
// Load the current value from the shared variable
// Load the thread-local private variable's value
// Perform the reduction operation
// Store the result back to the shared variable
call void @__kmpc_end_critical(...)
// Barrier after all threads complete their combinations
call void @__kmpc_barrier(...)
// Broadcast phase:
// Load the final result from the shared variable)
// Store the final result to the original private variable in each thread
// Final barrier after broadcast
call void @__kmpc_barrier(...)
```
---------
Co-authored-by: Chandra Ghale <ghale@pe31.hpc.amslabs.hpecorp.net>
The InstrProf headers are very expensive. Avoid including them in all of
CodeGen/ by moving the CodeGenPGO member behind a unqiue_ptr.
This reduces clang build time by 0.8%.
This fixes#139614 on non-clang compilers by moving `__has_warning`
completely inside the `#if defined(__clang__)` block. This prevents a
parse failure from compilers which don't recognize `__has_warning`.
Original description:
Followup to #138741.
This adds the requested macro to silence
`-Wunnecessary-virtual-specifier` when declaring virtual anchor
functions in `final` classes, per [LLVM
policy](https://llvm.org/docs/CodingStandards.html#provide-a-virtual-method-anchor-for-classes-in-headers).
It also cleans up any remaining instances of the warning, allowing us to
stop disabling it when we build LLVM.
This is quite ugly but it is the best I could think of. The old
FiniCBWrapper was way too brittle depending upon the exact block
structure inside of the section, and could be confused by any control
flow in the section (e.g. an if clause on cancel). The wording in the
comment and variable names didn't seem to match where it was actually
branching too as well.
Clang's (non-OpenMPIRBuilder) lowering for cancel inside of sections
branches to a block containing __kmpc_for_static_fini.
This was hard to achieve here because sometimes the FiniCBWrapper has to
run before the worksharing loop finalization has been crated.
To get around this ordering issue I created a dummy branch to a dummy
block, which is then fixed later once all of the information is
available.
This is an expensive header, only include it where needed. Move some
functions out of line to achieve that.
This reduces time to build clang by ~0.5% in terms of instructions
retired.
A proposed fix for the issue #95611, [OpenMP][SIMD] ordered has no
effect in a loop SIMD region as of LLVM 18.1.0
Changes:
- Implement new lowering behavior: Conservatively serialize "omp simd"
loops that have `omp simd ordered` directive to prevent incorrect
vectorization (which results in incorrect execution behavior of the
miscompiled program).
Implementation outline:
- We start with the optimistic default initial value of
`LoopStack.setParallel(/Enable=/true);` in
`CodeGenFunction::EmitOMPSimdInit(const OMPLoopDirective &D)`.
- We only disable the loop parallel memory access assumption with `if
(HasOrderedDirective) LoopStack.setParallel(/Enable=/false);` using the
`HasOrderedDirective` (which tests for the presence of an
`OMPOrderedDirective`).
- This results in no longer incorrectly vectorizing the loop when the
`omp simd ordered` directive is present.
Motivation: We'd like to prevent incorrect vectorization of the loops
marked with the `#pragma omp ordered simd` directive which has
previously resulted in miscompiled code.
At the same time, we'd like the usage outside of the `#pragma omp
ordered simd` context to remain unaffected: Note that in the test
"clang/test/OpenMP/ordered_codegen.cpp" we only "lose" the
`!llvm.access.group` metadata in `foo_simd` alone.
This is conservative, in that it's possible some of the loops would be
possible to vectorize, but we prefer to avoid miscompilation of the
loops that are currently illegal to vectorize.
A concrete example follows:
```cpp
// "test.c"
#include <float.h>
#include <math.h>
#include <omp.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
int compare_float(float x1, float x2, float scalar) {
const float diff = fabsf(x1 - x2);
x1 = fabsf(x1);
x2 = fabsf(x2);
const float l = (x2 > x1) ? x2 : x1;
if (diff <= l * scalar * FLT_EPSILON)
return 1;
else
return 0;
}
#define ARRAY_SIZE 256
__attribute__((noinline)) void initialization_loop(
float X[ARRAY_SIZE][ARRAY_SIZE], float Y[ARRAY_SIZE][ARRAY_SIZE]) {
const float max = 1000.0;
srand(time(NULL));
for (int r = 0; r < ARRAY_SIZE; r++) {
for (int c = 0; c < ARRAY_SIZE; c++) {
X[r][c] = ((float)rand() / (float)(RAND_MAX)) * max;
Y[r][c] = X[r][c];
}
}
}
__attribute__((noinline)) void omp_simd_loop(float X[ARRAY_SIZE][ARRAY_SIZE]) {
for (int r = 1; r < ARRAY_SIZE; ++r) {
for (int c = 1; c < ARRAY_SIZE; ++c) {
#pragma omp simd
for (int k = 2; k < ARRAY_SIZE; ++k) {
#pragma omp ordered simd
X[r][k] = X[r][k - 2] + sinf((float)(r / c));
}
}
}
}
__attribute__((noinline)) int comparison_loop(float X[ARRAY_SIZE][ARRAY_SIZE],
float Y[ARRAY_SIZE][ARRAY_SIZE]) {
int totalErrors_simd = 0;
const float scalar = 1.0;
for (int r = 1; r < ARRAY_SIZE; ++r) {
for (int c = 1; c < ARRAY_SIZE; ++c) {
for (int k = 2; k < ARRAY_SIZE; ++k) {
Y[r][k] = Y[r][k - 2] + sinf((float)(r / c));
}
}
// check row for simd update
for (int k = 0; k < ARRAY_SIZE; ++k) {
if (!compare_float(X[r][k], Y[r][k], scalar)) {
++totalErrors_simd;
}
}
}
return totalErrors_simd;
}
int main(void) {
float X[ARRAY_SIZE][ARRAY_SIZE];
float Y[ARRAY_SIZE][ARRAY_SIZE];
initialization_loop(X, Y);
omp_simd_loop(X);
const int totalErrors_simd = comparison_loop(X, Y);
if (totalErrors_simd) {
fprintf(stdout, "totalErrors_simd: %d \n", totalErrors_simd);
fprintf(stdout, "%s : %d - FAIL: error in ordered simd computation.\n",
__FILE__, __LINE__);
} else {
fprintf(stdout, "Success!\n");
}
return totalErrors_simd;
}
```
Before:
```
$ clang -fopenmp-simd -O3 -ffast-math -lm test.c -o test && ./test
totalErrors_simd: 15408
test.c : 76 - FAIL: error in ordered simd computation.
```
clang 19.1.0: https://godbolt.org/z/6EvhxqEhe
After:
```
$ clang -fopenmp-simd -O3 -ffast-math test.c -o test && ./test
Success!
```
Co-authored-by: Matt P. Dziubinski <matt-p.dziubinski@hpe.com>
A proposed fix for #95611 [OpenMP][SIMD] ordered has no effect in a loop
SIMD region as of LLVM 18.1.0
Changes:
- Implement new lowering behavior: Conservatively serialize "omp simd"
loops that have `omp simd ordered` directive to prevent incorrect
vectorization (which results in incorrect execution behavior of the
miscompiled program).
Implementation outline:
- We start with the optimistic default initial value of
`LoopStack.setParallel(/Enable=/true);` in
`CodeGenFunction::EmitOMPSimdInit(const OMPLoopDirective &D)`.
- We only disable the loop parallel memory access assumption with `if
(HasOrderedDirective) LoopStack.setParallel(/Enable=/false);` using the
`HasOrderedDirective` (which tests for the presence of an
`OMPOrderedDirective`).
- This results in no longer incorrectly vectorizing the loop when the
`omp simd ordered` directive is present.
Motivation: We'd like to prevent incorrect vectorization of the loops
marked with the `#pragma omp ordered simd` directive which has
previously resulted in miscompiled code.
At the same time, we'd like the usage outside of the `#pragma omp
ordered simd` context to remain unaffected: Note that in the test
"clang/test/OpenMP/ordered_codegen.cpp" we only "lose" the
`!llvm.access.group` metadata in `foo_simd` alone.
This is conservative, in that it's possible some of the loops would be
possible to vectorize, but we prefer to avoid miscompilation of the
loops that are currently illegal to vectorize.
A concrete example follows:
```cpp
// "test.c"
#include <float.h>
#include <math.h>
#include <omp.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
int compare_float(float x1, float x2, float scalar) {
const float diff = fabsf(x1 - x2);
x1 = fabsf(x1);
x2 = fabsf(x2);
const float l = (x2 > x1) ? x2 : x1;
if (diff <= l * scalar * FLT_EPSILON)
return 1;
else
return 0;
}
#define ARRAY_SIZE 256
__attribute__((noinline)) void initialization_loop(
float X[ARRAY_SIZE][ARRAY_SIZE], float Y[ARRAY_SIZE][ARRAY_SIZE]) {
const float max = 1000.0;
srand(time(NULL));
for (int r = 0; r < ARRAY_SIZE; r++) {
for (int c = 0; c < ARRAY_SIZE; c++) {
X[r][c] = ((float)rand() / (float)(RAND_MAX)) * max;
Y[r][c] = X[r][c];
}
}
}
__attribute__((noinline)) void omp_simd_loop(float X[ARRAY_SIZE][ARRAY_SIZE]) {
for (int r = 1; r < ARRAY_SIZE; ++r) {
for (int c = 1; c < ARRAY_SIZE; ++c) {
#pragma omp simd
for (int k = 2; k < ARRAY_SIZE; ++k) {
#pragma omp ordered simd
X[r][k] = X[r][k - 2] + sinf((float)(r / c));
}
}
}
}
__attribute__((noinline)) int comparison_loop(float X[ARRAY_SIZE][ARRAY_SIZE],
float Y[ARRAY_SIZE][ARRAY_SIZE]) {
int totalErrors_simd = 0;
const float scalar = 1.0;
for (int r = 1; r < ARRAY_SIZE; ++r) {
for (int c = 1; c < ARRAY_SIZE; ++c) {
for (int k = 2; k < ARRAY_SIZE; ++k) {
Y[r][k] = Y[r][k - 2] + sinf((float)(r / c));
}
}
// check row for simd update
for (int k = 0; k < ARRAY_SIZE; ++k) {
if (!compare_float(X[r][k], Y[r][k], scalar)) {
++totalErrors_simd;
}
}
}
return totalErrors_simd;
}
int main(void) {
float X[ARRAY_SIZE][ARRAY_SIZE];
float Y[ARRAY_SIZE][ARRAY_SIZE];
initialization_loop(X, Y);
omp_simd_loop(X);
const int totalErrors_simd = comparison_loop(X, Y);
if (totalErrors_simd) {
fprintf(stdout, "totalErrors_simd: %d \n", totalErrors_simd);
fprintf(stdout, "%s : %d - FAIL: error in ordered simd computation.\n",
__FILE__, __LINE__);
} else {
fprintf(stdout, "Success!\n");
}
return totalErrors_simd;
}
```
Before:
```
$ clang -fopenmp-simd -O3 -ffast-math -lm test.c -o test && ./test
totalErrors_simd: 15408
test.c : 76 - FAIL: error in ordered simd computation.
```
clang 19.1.0: https://godbolt.org/z/6EvhxqEhe
After:
```
$ clang -fopenmp-simd -O3 -ffast-math test.c -o test && ./test
Success!
```
Co-authored-by: Matt P. Dziubinski <matt-p.dziubinski@hpe.com>
The preprocessor definition used to enable asserts and the one that
`llvm::Error` and `llvm::Expected` use to ensure all created instances are
checked are not the same. By making these checks inside of an `assert` in cases
where errors are not expected, certain build configurations would trigger
runtime failures (e.g. `-DLLVM_ENABLE_ASSERTIONS=OFF
-DLLVM_UNREACHABLE_OPTIMIZE=ON`).
The `llvm::cantFail()` function, which was intended for this use case, is used
by this patch in place of `assert` to prevent these runtime failures. In tests,
new preprocessor definitions based on `ASSERT_THAT_EXPECTED` and
`EXPECT_THAT_EXPECTED` are used instead, to avoid silent failures in release
builds.
Initial parsing/sema for 'strict' modifier with 'num_tasks' and
‘grainsize’ clause is present in these commits
[grainsize_parsing](ab9eac762c)
and
[num_tasks_parsing](56c1660170 (diff-4184486638e85284c3a2c961a81e7752231022daf97e411007c13a6732b50db9R6545))
. However, this implementation appears incomplete as it lacks code
generation support. A runtime patch was introduced in this runtime
commit
[runtime_patch](540007b427 (diff-5e95f9319910d6965d09c301359dbe6b23f3eef5ce4d262ef2c2d2137875b5c4R374))
, which adds a new API, _kmpc_taskloop_5, to accommodate the strict
modifier.
In this patch I have added codegen support. When the strict modifier is
present alongside the grainsize or num_tasks clauses of taskloop
construct, the code now emits a call to _kmpc_taskloop_5, which includes
an additional parameter of type i32 with the value 1 to indicate the
strict modifier. If the strict modifier is not present, it falls back to
the existing _kmpc_taskloop API call.
---------
Co-authored-by: Chandra Ghale <ghale@pe31.hpc.amslabs.hpecorp.net>
This patch implements an approach to communicate errors between the
OMPIRBuilder and its users. It introduces `llvm::Error` and
`llvm::Expected` objects to replace the values returned by callbacks
passed to `OMPIRBuilder` codegen functions. These functions then check
the result for errors when callbacks are called and forward them back to
the caller, which has the flexibility to recover, exit cleanly or dump a
stack trace.
This prevents a failed callback to leave the IR in an invalid state and
still continue the codegen process, triggering unrelated assertions or
segmentation faults. In the case of MLIR to LLVM IR translation of the
'omp' dialect, this change results in the compiler emitting errors and
exiting early instead of triggering a crash for not-yet-implemented
errors. The behavior in Clang and openmp-opt stays unchanged, since
callbacks will continue always returning 'success'.
Added codegen for scope directive, enabled allocate and firstprivate
clauses, and added scope directive LIT test.
Testing
- LIT tests (including new scope test).
- OpenMP scope example test from 5.2 OpenMP API examples document.
- Three executable scope tests from OpenMP_VV/sollve_vv suite.
By the OpenMP standard, `num_teams` clause can only accept one
expression (for now). In this patch, we extend it to allow to accept
multiple expressions when it is used with `target teams ompx_bare`
construct. This will allow to launch a multi-dim grid, same as CUDA/HIP.
This is a minimal patch to support parsing for "omp assume" directives.
These are meant to be hints to a compiler's optimisers: as such, it is
legitimate (if not very useful) to ignore them. The patch builds on top
of the existing support for "omp assumes" directives (note spelling!).
Unlike the "omp [begin/end] assumes" directives, "omp assume" is
associated with a compound statement, i.e. it can appear within a
function. The "holds" assumption could (theoretically) be mapped onto
the existing builtin "__builtin_assume", though the latter applies to a
single point in the program, and the former to a range (i.e. the whole
of the associated compound statement).
This patch fixes sollve's OpenMP 5.1 "omp assume"-based tests.
Use this to replace the emission of the amdgpu-unsafe-fp-atomics
attribute in favor of per-instruction metadata. In the future
new fine grained controls should be introduced that also cover
the integer cases.
Add a wrapper around CreateAtomicRMW that appends the metadata,
and update a few use contexts to use it.
In debug mode there is a wrapper (the kernel) around the function in
which we generate the kernel code. We worked around this before to get
the correct kernel name, but now we really distinguish both to attach
the launch bounds to the kernel, not the inner function.
Given "loop" construct, clang will try to treat it as "for",
"distribute" or "simd", depending on either the implied binding, or the
bind clause if present. This patch moves the code that performs this
construct remapping from sema to codegen.
For a "loop" construct without a bind clause, this patch will create an
implicit bind clause based on implied binding to simplify further
analysis.
During codegen the function `EmitOMPGenericLoopDirective` (i.e. "loop")
will invoke the "emit" functions for "for", "distribute" or "simd",
depending on the bind clause.
---------
Co-authored-by: Alexey Bataev <a.bataev@gmx.com>
Add the reverse directive which will be introduced in the upcoming
OpenMP 6.0 specification. A preview has been published in [Technical
Report 12](https://www.openmp.org/wp-content/uploads/openmp-TR12.pdf).
---------
Co-authored-by: Alexey Bataev <a.bataev@outlook.com>
Summary:
The parsing for this was implemented, but we never hooked up the default
value to the result of this clause. This patch adds the support by
making it default to the requires directive.
This patch just fixes a few spelling mistakes in the above two files. (I
changed one British spelling to American -- analyse to analyze --
because the latter spelling is used elsewhere in file, and it's probably
best to be consistent.)
OpenMP loop transformation did not work on a for-loop using an iterator
or range-based for-loops. The first reason is that it combined the
iterator's type for generated loops with the type of `NumIterations` as
generated for any `OMPLoopBasedDirective` which is an integer. Fixed by
basing all generated loop variables on `NumIterations`.
Second, C++11 range-based for-loops include syntactic sugar that needs
to be executed before the loop. This additional code is now added to the
construct's Pre-Init lists.
Third, C++20 added an initializer statement to range-based for-loops
which is also added to the pre-init statement. PreInits used to be a
`DeclStmt` which made it difficult to add arbitrary statements from
`CXXRangeForStmt`'s syntactic sugar, especially the for-loops init
statement which does not need to be a declaration. Change it to be a
general `Stmt` that can be a `CompoundStmt` to hold arbitrary Stmts,
including DeclStmts. This also avoids the `PointerUnion` workaround used
by `checkTransformableLoopNest`.
End-to-end tests are added to verify the expected number and order of
loop execution and evaluations of expressions (such as iterator
dereference). The order and number of evaluations of expressions in
canonical loops is explicitly undefined by OpenMP but checked here for
clarification and for changes to be noticed.
This is in effect a revert of f139ae3d93797, as we have since gained a
more sophisticated way of doing extra IRGen with the addition of
RawAddress in #86923.
OpenACC is going to need an array sections implementation that is a
simpler version/more restrictive version of the OpenMP version.
This patch moves `OMPArraySectionExpr` to `Expr.h` and renames it `ArraySectionExpr`,
then adds an enum to choose between the two.
This also fixes a couple of 'drive-by' issues that I discovered on the way,
but leaves the OpenACC Sema parts reasonably unimplemented (no semantic
analysis implementation), as that will be a followup patch.
IR for 'target teams loop' is now dependent on suitability of associated
loop-nest.
If a loop-nest:
- does not contain a function call, or
- the -fopenmp-assume-no-nested-parallelism has been specified,
- or the call is to an OpenMP API AND
- does not contain nested loop bind(parallel) directives
then it can be emitted as 'target teams distribute parallel for', which
is the current default. Otherwise, it is emitted as 'target teams
distribute'.
Added debug output indicating how 'target teams loop' was emitted. Flag
is -mllvm -debug-only=target-teams-loop-codegen
Added LIT tests explicitly verifying 'target teams loop' emitted as a
parallel loop and a distribute loop.
Updated other 'loop' related tests as needed to reflect change in IR.
- These updates account for most of the changed files and
additions/deletions.
To authenticate pointers, CodeGen needs access to the key and
discriminators that were used to sign the pointer. That information is
sometimes known from the context, but not always, which is why `Address`
needs to hold that information.
This patch adds methods and data members to `Address`, which will be
needed in subsequent patches to authenticate signed pointers, and uses
the newly added methods throughout CodeGen. Although this patch isn't
strictly NFC as it causes CodeGen to use different code paths in some
cases (e.g., `mergeAddressesInConditionalExpr`), it doesn't cause any
changes in functionality as it doesn't add any information needed for
authentication.
In addition to the changes mentioned above, this patch introduces class
`RawAddress`, which contains a pointer that we know is unsigned, and
adds several new functions for creating `Address` and `LValue` objects.
This reapplies d9a685a9dd589486e882b722e513ee7b8c84870c, which was
reverted because it broke ubsan bots. There seems to be a bug in
coroutine code-gen, which is causing EmitTypeCheck to use the wrong
alignment. For now, pass alignment zero to EmitTypeCheck so that it can
compute the correct alignment based on the passed type (see function
EmitCXXMemberOrOperatorMemberCallExpr).
To authenticate pointers, CodeGen needs access to the key and
discriminators that were used to sign the pointer. That information is
sometimes known from the context, but not always, which is why `Address`
needs to hold that information.
This patch adds methods and data members to `Address`, which will be
needed in subsequent patches to authenticate signed pointers, and uses
the newly added methods throughout CodeGen. Although this patch isn't
strictly NFC as it causes CodeGen to use different code paths in some
cases (e.g., `mergeAddressesInConditionalExpr`), it doesn't cause any
changes in functionality as it doesn't add any information needed for
authentication.
In addition to the changes mentioned above, this patch introduces class
`RawAddress`, which contains a pointer that we know is unsigned, and
adds several new functions for creating `Address` and `LValue` objects.
This reapplies 8bd1f9116aab879183f34707e6d21c7051d083b6. The commit
broke msan bots because LValue::IsKnownNonNull was uninitialized.
To authenticate pointers, CodeGen needs access to the key and
discriminators that were used to sign the pointer. That information is
sometimes known from the context, but not always, which is why `Address`
needs to hold that information.
This patch adds methods and data members to `Address`, which will be
needed in subsequent patches to authenticate signed pointers, and uses
the newly added methods throughout CodeGen. Although this patch isn't
strictly NFC as it causes CodeGen to use different code paths in some
cases (e.g., `mergeAddressesInConditionalExpr`), it doesn't cause any
changes in functionality as it doesn't add any information needed for
authentication.
In addition to the changes mentioned above, this patch introduces class
`RawAddress`, which contains a pointer that we know is unsigned, and
adds several new functions for creating `Address` and `LValue` objects.
This is the major rename patch that prior patches have built towards.
The DPValue class is being renamed to DbgVariableRecord, which reflects
the updated terminology for the "final" implementation of the RemoveDI
feature. This is a pure string substitution + clang-format patch. The
only manual component of this patch was determining where to perform
these string substitutions: `DPValue` and `DPV` are almost exclusively
used for DbgRecords, *except* for:
- llvm/lib/target, where 'DP' is used to mean double-precision, and so
appears as part of .td files and in variable names. NB: There is a
single existing use of `DPValue` here that refers to debug info, which
I've manually updated.
- llvm/tools/gold, where 'LDPV' is used as a prefix for symbol
visibility enums.
Outside of these places, I've applied several basic string
substitutions, with the intent that they only affect DbgRecord-related
identifiers; I've checked them as I went through to verify this, with
reasonable confidence that there are no unintended changes that slipped
through the cracks. The substitutions applied are all case-sensitive,
and are applied in the order shown:
```
DPValue -> DbgVariableRecord
DPVal -> DbgVarRec
DPV -> DVR
```
Following the previous rename patches, it should be the case that there
are no instances of any of these strings that are meant to refer to the
general case of DbgRecords, or anything other than the DPValue class.
The idea behind this patch is therefore that pure string substitution is
correct in all cases as long as these assumptions hold.
This patch fixes problems that pop up when clang emits DbgRecords
instead of debug intrinsics.
Note: this doesn't mean clang is emitting DbgRecords yet, because the
modules it creates are still always in the old debug mode. That will
come in a future patch.
Depends on #84739
