#version 450

#extension GL_EXT_shader_16bit_storage : require
#extension GL_EXT_spirv_intrinsics: enable
#extension GL_EXT_control_flow_attributes : require

#if RTE16
spirv_execution_mode(capabilities = [4467], 4462, 16); // RoundingModeRTE, 16 bits
#endif

layout (push_constant) uniform parameter
{
    uint batch_offset; uint offset_delta;
    uint IC;
    uint IW; uint IH;
    uint OW; uint OH;
    uint KW; uint KH;
    uint pelements;
    uint CHW;
    int s0; int s1;
    int p0; int p1;
    int d0; int d1;
} p;

#include "types.comp"

layout(constant_id = 0) const uint BLOCK_SIZE = 32;

const uint NUM_ITER = 512 / BLOCK_SIZE;

layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;

layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};

void main() {
    const uint gidx = gl_GlobalInvocationID.x;

    const uint oh = gl_GlobalInvocationID.y;
    const uint batch = gl_GlobalInvocationID.z / p.IC;
    const uint ic = gl_GlobalInvocationID.z % p.IC;

    const uint src_base = ic * p.offset_delta + batch * p.batch_offset;
    const uint dst_base = ((batch * p.OH + oh) * p.OW) * p.CHW + ic * (p.KW * p.KH);
    const int oh_s1 = int(oh) * p.s1;
    const uint ksize = p.OW * (p.KH > 1 ? p.KW : 1);

    const uint base_linear_idx = gidx * NUM_ITER;

    const uint max_ky = ksize / p.OW;

    uint current_kx = base_linear_idx / ksize;
    const uint rem = base_linear_idx - (current_kx * ksize);
    uint current_ky = rem / p.OW;
    uint current_ix = rem % p.OW;

    A_TYPE values[NUM_ITER];
    uint offset_dst[NUM_ITER];
    [[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {
        values[idx] = A_TYPE(0);
    }

    [[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {

        const uint linear_idx = base_linear_idx + idx;

        if (linear_idx >= p.pelements) {
            continue;
        }

        const uint iiw = current_ix * p.s0 + current_kx * p.d0 - p.p0;
        const uint iih = oh_s1 + current_ky * p.d1 - p.p1;

        offset_dst[idx] = dst_base + current_ix * p.CHW + current_ky * p.KW + current_kx;

        if ((iih < p.IH) && (iiw < p.IW)) {
            values[idx] = data_a[src_base + iih * p.IW + iiw];
        }

        if (++current_ix == p.OW) {
            current_ix = 0;
            if (++current_ky == max_ky) {
                current_ky = 0;
                current_kx++;
            }
        }
    }

    [[unroll]] for (uint idx = 0; idx < NUM_ITER; ++idx) {

        const uint linear_idx = base_linear_idx + idx;

        if (linear_idx >= p.pelements) {
            continue;
        }

        data_d[offset_dst[idx]] = D_TYPE(values[idx]);
    }

}