Unverified Commit 8b793f7e authored by ekuznetsov139's avatar ekuznetsov139 Committed by GitHub
Browse files

MI325 configs, fused_moe_kernel bugfix (#14987)


Signed-off-by: default avatarEugene Kuznetsov <eugene.kuznetsov@amd.com>
parent af35d3a3
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 16,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 16,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 32,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 16,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"4": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 8,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
......@@ -783,8 +783,12 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
use_int8_w8a16=use_int8_w8a16,
**config,
)
else:
config = config.copy()
BLOCK_SIZE_K = config.pop("BLOCK_SIZE_K")
if block_shape is not None:
BLOCK_SIZE_K = min(BLOCK_SIZE_K, min(block_shape[0],
block_shape[1]))
fused_moe_kernel[grid](
A,
B,
......@@ -823,6 +827,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
compute_type=compute_type,
use_fp8_w8a8=use_fp8_w8a8,
use_int8_w8a16=use_int8_w8a16,
BLOCK_SIZE_K=BLOCK_SIZE_K,
**config,
)
......
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
{
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"24": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"48": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 8,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"96": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 16,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"512": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"1536": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"3072": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"GROUP_SIZE_M": 32,
"kpack": 1,
"matrix_instr_nonkdim": 16,
"num_warps": 4
}
}
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment