//TEST_CATEGORY(wave-mask, compute)
//DISABLE_TEST:COMPARE_COMPUTE_EX:-cpu -compute -shaderobj
//DISABLE_TEST:COMPARE_COMPUTE_EX:-slang -compute -shaderobj
//TEST:COMPARE_COMPUTE_EX:-slang -compute -dx12 -profile cs_6_0 -shaderobj
//TEST(vulkan):COMPARE_COMPUTE_EX:-vk -compute -shaderobj
//TEST:COMPARE_COMPUTE_EX:-cuda -compute -shaderobj
//TEST:COMPARE_COMPUTE_EX:-metal -compute -shaderobj

//TEST_INPUT:ubuffer(data=[0 0 0 0 0 0 0 0], stride=4):out,name outputBuffer
RWStructuredBuffer<int> outputBuffer;

[numthreads(4, 1, 1)]
void computeMain(uint3 dispatchThreadID : SV_DispatchThreadID)
{
    int idx = int(dispatchThreadID.x);
    
    WaveMask mask = WaveGetActiveMask();
    uint4 multi = WaveGetActiveMulti();
    
    // Should be 0xf, because numthreads is 4, 1, 1
    outputBuffer[idx * 2 + 0] = int(mask);
    outputBuffer[idx * 2 + 1] = int(multi.x);
}