commit a1826b4d2603a2018ca348d430159ec59e0b72bd
author Matt <MattPD@users.noreply.github.com> Wed Feb 12 07:53:47 2025 -0600
committer GitHub <noreply@github.com> Wed Feb 12 08:53:47 2025 -0500
tree bafaead2b07f28ff9defec80ca3e548ac007e983
parent f3a1d558116904b793ff8ece7dae9605b741b178

[OpenMP][SIMD][FIX] Use conservative "omp simd ordered" lowering (#126172)

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>