#version 450

/*
 * Iris Vulkan GEMM (f32)
 *
 * Computes C[M,N] = alpha * op(A)[M,K] @ op(B)[K,N] + beta * C[M,N]
 * where op() optionally transposes, matching the BLAS sgemm contract used
 * by the Iris kernels layer. Tiled with 16x16 shared-memory blocks.
 *
 * A, B, C are row-major with leading dims lda, ldb, ldc.
 */

layout(local_size_x = 16, local_size_y = 16) in;

layout(std430, binding = 0) readonly buffer ABuf { float A[]; };
layout(std430, binding = 1) readonly buffer BBuf { float B[]; };
layout(std430, binding = 2) buffer CBuf { float C[]; };

layout(push_constant) uniform PC {
    uint M, N, K;
    uint lda, ldb, ldc;
    uint ta, tb;
    float alpha, beta;
} pc;

shared float As[16][16];
shared float Bs[16][16];

void main() {
    uint row = gl_GlobalInvocationID.y;
    uint col = gl_GlobalInvocationID.x;
    uint tx = gl_LocalInvocationID.x;
    uint ty = gl_LocalInvocationID.y;

    float acc = 0.0;
    uint numTiles = (pc.K + 15u) / 16u;

    for (uint t = 0u; t < numTiles; t++) {
        uint kA = t * 16u + tx;   /* column of A loaded by this lane */
        uint kB = t * 16u + ty;   /* row of B loaded by this lane */

        float av = 0.0;
        if (row < pc.M && kA < pc.K) {
            av = (pc.ta == 0u) ? A[row * pc.lda + kA]
                               : A[kA * pc.lda + row];
        }
        As[ty][tx] = av;

        float bv = 0.0;
        if (col < pc.N && kB < pc.K) {
            bv = (pc.tb == 0u) ? B[kB * pc.ldb + col]
                               : B[col * pc.ldb + kB];
        }
        Bs[ty][tx] = bv;

        barrier();

        for (uint k = 0u; k < 16u; k++) {
            acc += As[ty][k] * Bs[k][tx];
        }

        barrier();
    }

    if (row < pc.M && col < pc.N) {
        uint ci = row * pc.ldc + col;
        float prev = (pc.beta != 0.0) ? C[ci] : 0.0;
        C[ci] = pc.alpha * acc + pc.beta * prev;
    }
}