#version 450 core
#extension GL_KHR_memory_scope_semantics : enable
#extension GL_NV_cooperative_matrix : enable
#extension GL_EXT_shader_explicit_arithmetic_types_float16 : enable

#pragma use_variable_pointers

layout (local_size_x = 64, local_size_y = 1, local_size_z = 1) in;

layout(set = 0, binding = 0) coherent buffer Block {
    float y[1024*1024];
    float x[];
} block;


void main()
{
    fcoopmatNV<32, gl_ScopeSubgroup, 16, 8> m = fcoopmatNV<32, gl_ScopeSubgroup, 16, 8>(0.0);

    m = m + m;
    m = m - m;
    m = -m;
    m = 2.0*m;
    m = m*2.0;

    coopMatLoadNV(m, block.x, 16, 128, false);
    coopMatStoreNV(m, block.x, 16, 128, false);
}