Synchronization between FPU and INT pipelines for arbitrary C code

[and-ivanov]

The output of cycle-accurate simulation for this code is not correct:

#include <snrt.h>
#include <printf.h>
#define f64 double
#define i32 int

#define B 2
#define N 32

void __attribute__((noinline)) my_func(double* x, double* y) {
    for (int n = 0; n < N; n++) {
        for (int b = 0; b < B; b++) {
            x[b * N + n] *= y[b];
        }
    }
    for (int b = 0; b < B; b++) {
        y[b] = 0;
    }
}

int main() {
    unsigned tid = snrt_cluster_core_idx();
    if (tid != 0) {
        return 0;
    }
    double* y = (f64*) snrt_l1alloc(B * sizeof(f64));
    double* x = (f64*) snrt_l1alloc(B * N * sizeof(f64));
    double* z = (f64*) snrt_l1alloc(B * N * sizeof(f64));
    y[0] = 3.0;
    y[1] = 2.0;
    for (int n = 0; n < N; n++) {
        for (int b = 0; b < B; b++) {
            x[b * N + n] = n + 1;
            z[b * N + n] = (n + 1) * y[b];
        }
    }
    my_func(x, y);
    i32 ok = 1;
    for (int i = 0; i < B * N; i++) {
        if ((x[i] - z[i]) * (x[i] - z[i]) > 1e-3) {
            printf("Error: mismatch at dst, %d, %f (computed) != %f (expected) \n", (int)i, (double)x[i], (double)z[i]);
            ok = 0;
            break;
        }
    }
    if (ok) {
        printf("success, exitting...\n");
        return 0;
    } else {
        printf("FAILURE, exitting...\n");
        return 1;
    }
}

Observed output:

Error: mismatch at dst, 31, 0.000000 (computed) != 96.000000 (expected)

The issue is suspected to come from the lack of synchronization between INT and FPU units. It can be seen from the assembly https://godbolt.org/z/z3oEz4aen that no synchronization is even supposed to happen.

my_func:                                # @my_func
        fld     ft0, 0(a1)  # everything below goes to FPU 
        fld     ft1, 0(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 0(a0)
        fld     ft0, 8(a1)
        fld     ft1, 32(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 32(a0)
        fld     ft0, 0(a1)
        fld     ft1, 8(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 8(a0)
        fld     ft0, 8(a1)
        fld     ft1, 40(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 40(a0)
        fld     ft0, 0(a1)
        fld     ft1, 16(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 16(a0)
        fld     ft0, 8(a1)
        fld     ft1, 48(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 48(a0)
        fld     ft0, 0(a1)
        fld     ft1, 24(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 24(a0)
        fld     ft0, 8(a1)
        fld     ft1, 56(a0)
        fmul.d  ft0, ft0, ft1
        fsd     ft0, 56(a0)
        sw      zero, 12(a1)  # everything below goes to INT
        sw      zero, 8(a1)
        sw      zero, 4(a1)
        sw      zero, 0(a1)
        ret

[colluca]

This issue is currently being addressed in https://github.com/pulp-platform/snitch_cluster/pull/90.

[colluca]

Solved in https://github.com/pulp-platform/snitch_cluster/pull/90.