Function ggml_compute_forward_sub_f32

ggml.c:7677–7735

// ggml_compute_forward_sub

static void ggml_compute_forward_sub_f32(
        const struct ggml_compute_params * params,
        const struct ggml_tensor * src0,
        const struct ggml_tensor * src1,
        struct ggml_tensor * dst) {
    assert(params->ith == 0);
    assert(ggml_are_same_shape(src0, src1) && ggml_are_same_shape(src0, dst));

    if (params->type == GGML_TASK_INIT || params->type == GGML_TASK_FINALIZE) {
        return;
    }

    const int nr  = ggml_nrows(src0);

    GGML_TENSOR_BINARY_OP_LOCALS

    GGML_ASSERT( nb0 == sizeof(float));
    GGML_ASSERT(nb00 == sizeof(float));

    if (nb10 == sizeof(float)) {
        for (int ir = 0; ir < nr; ++ir) {
            // src0, src1 and dst are same shape => same indices
            const int i3 = ir/(ne2*ne1);
            const int i2 = (ir - i3*ne2*ne1)/ne1;
            const int i1 = (ir - i3*ne2*ne1 - i2*ne1);

#ifdef GGML_USE_ACCELERATE
            vDSP_vsub(
                    (float *) ((char *) src1->data + i3*nb13 + i2*nb12 + i1*nb11), 1,
                    (float *) ((char *) src0->data + i3*nb03 + i2*nb02 + i1*nb01), 1,
                    (float *) ((char *) dst->data  + i3*nb3  + i2*nb2  + i1*nb1 ), 1,
                    ne0);
#else
            ggml_vec_sub_f32(ne0,
                    (float *) ((char *) dst->data  + i3*nb3  + i2*nb2  + i1*nb1 ),
                    (float *) ((char *) src0->data + i3*nb03 + i2*nb02 + i1*nb01),
                    (float *) ((char *) src1->data + i3*nb13 + i2*nb12 + i1*nb11));
#endif
                // }
            // }
        }
    } else {
        // src1 is not contiguous
        for (int ir = 0; ir < nr; ++ir) {
            // src0, src1 and dst are same shape => same indices
            const int i3 = ir/(ne2*ne1);
            const int i2 = (ir - i3*ne2*ne1)/ne1;
            const int i1 = (ir - i3*ne2*ne1 - i2*ne1);

            float * dst_ptr  = (float *) ((char *) dst->data  + i3*nb3  + i2*nb2  + i1*nb1 );
            float * src0_ptr = (float *) ((char *) src0->data + i3*nb03 + i2*nb02 + i1*nb01);
            for (int i0 = 0; i0 < ne0; i0++) {
                float * src1_ptr = (float *) ((char *) src1->data + i3*nb13 + i2*nb12 + i1*nb11 + i0*nb10);

                dst_ptr[i0] = src0_ptr[i0] - *src1_ptr;
            }
        }
    }