And I'm wondering why?, as it is hiding what exactly is reported by the check feature just before
D3D12_FEATURE_DATA_WAVE_MMA:
----------------------------
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_BYTE, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 10
AccumDataTypes = 0x6
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT16
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT
RequiredWaveLaneCountMin = 1
RequiredWaveLaneCountMax = 2
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_FLOAT16, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 10
AccumDataTypes = 0x6
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT16
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT
RequiredWaveLaneCountMin = 1
RequiredWaveLaneCountMax = 2
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_FLOAT, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 10
AccumDataTypes = 0x6
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT16
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT
RequiredWaveLaneCountMin = 1
RequiredWaveLaneCountMax = 2
D3D12_FEATURE_DATA_WAVE_MMA:
----------------------------
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_BYTE, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 16
AccumDataTypes = 0x1
D3D12_WAVE_MMA_ACCUM_DATATYPE_INT32
RequiredWaveLaneCountMin = 32
RequiredWaveLaneCountMax = 64
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_FLOAT16, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 16
AccumDataTypes = 0x2
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT16
RequiredWaveLaneCountMin = 32
RequiredWaveLaneCountMax = 64
InputDataType = D3D12_WAVE_MMA_INPUT_DATATYPE_FLOAT, M = D3D12_WAVE_MMA_DIMENSION_16, N = D3D12_WAVE_MMA_DIMENSION_16:
Supported = TRUE
K = 16
AccumDataTypes = 0x4
D3D12_WAVE_MMA_ACCUM_DATATYPE_FLOAT
RequiredWaveLaneCountMin = 32
RequiredWaveLaneCountMax = 64
Can submit a small PR to fix it if you want.