Unverified Commit bf21481d authored by Divakar Verma's avatar Divakar Verma Committed by GitHub
Browse files

[ROCm][MoE] MI300 tuned configs Mixtral-8x(7B,22B) | fp16, fp8 (#12408)


Signed-off-by: default avatarDivakar Verma <divakar.verma@amd.com>
parent fb30ee92
{
"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
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"4": {
"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
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{ {
"1": { "1": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"2": { "2": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -23,10 +23,10 @@ ...@@ -23,10 +23,10 @@
}, },
"4": { "4": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 1,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -34,10 +34,10 @@ ...@@ -34,10 +34,10 @@
}, },
"8": { "8": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 1, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -48,7 +48,7 @@ ...@@ -48,7 +48,7 @@
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -56,10 +56,10 @@ ...@@ -56,10 +56,10 @@
}, },
"24": { "24": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 1, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -67,32 +67,32 @@ ...@@ -67,32 +67,32 @@
}, },
"32": { "32": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 2, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"48": { "48": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"64": { "64": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -100,24 +100,24 @@ ...@@ -100,24 +100,24 @@
}, },
"96": { "96": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 4, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"128": { "128": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 32,
"kpack": 2 "kpack": 2
}, },
"256": { "256": {
...@@ -129,7 +129,7 @@ ...@@ -129,7 +129,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"512": { "512": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -150,7 +150,7 @@ ...@@ -150,7 +150,7 @@
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 32, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 2
}, },
"1536": { "1536": {
...@@ -184,7 +184,7 @@ ...@@ -184,7 +184,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"4096": { "4096": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -195,6 +195,6 @@ ...@@ -195,6 +195,6 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
} }
} }
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"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
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"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
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 1,
"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": 2,
"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": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 128,
"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
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 4,
"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": 4,
"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": 16,
"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": 16,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"2": {
"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
},
"4": {
"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
},
"8": {
"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
},
"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
},
"24": {
"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
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"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
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{ {
"1": { "1": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -19,14 +19,14 @@ ...@@ -19,14 +19,14 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"4": { "4": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -34,76 +34,76 @@ ...@@ -34,76 +34,76 @@
}, },
"8": { "8": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"16": { "16": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"24": { "24": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"32": { "32": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"48": { "48": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 2
}, },
"64": { "64": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"96": { "96": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -112,24 +112,24 @@ ...@@ -112,24 +112,24 @@
"128": { "128": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"256": { "256": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"512": { "512": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
...@@ -151,7 +151,7 @@ ...@@ -151,7 +151,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"1536": { "1536": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -162,7 +162,7 @@ ...@@ -162,7 +162,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"2048": { "2048": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -184,7 +184,7 @@ ...@@ -184,7 +184,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"4096": { "4096": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -195,6 +195,6 @@ ...@@ -195,6 +195,6 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "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
},
"2": {
"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
},
"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
},
"8": {
"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
},
"16": {
"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
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"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
},
"64": {
"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
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"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
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{
"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": 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": 2
},
"4": {
"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
},
"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": 32,
"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
},
"24": {
"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": 1
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"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": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"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": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 64,
"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": 32,
"kpack": 2
},
"1024": {
"BLOCK_SIZE_M": 128,
"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
},
"1536": {
"BLOCK_SIZE_M": 128,
"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
},
"2048": {
"BLOCK_SIZE_M": 128,
"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
},
"3072": {
"BLOCK_SIZE_M": 128,
"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
},
"4096": {
"BLOCK_SIZE_M": 128,
"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
}
}
{
"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
},
"2": {
"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
},
"4": {
"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
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"24": {
"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
},
"32": {
"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
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"64": {
"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
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
}
}
{ {
"1": { "1": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"2": { "2": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -23,10 +23,10 @@ ...@@ -23,10 +23,10 @@
}, },
"4": { "4": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -34,7 +34,7 @@ ...@@ -34,7 +34,7 @@
}, },
"8": { "8": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 2,
...@@ -52,32 +52,32 @@ ...@@ -52,32 +52,32 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"24": { "24": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"32": { "32": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 2, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"48": { "48": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
...@@ -85,7 +85,7 @@ ...@@ -85,7 +85,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"64": { "64": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
...@@ -101,40 +101,40 @@ ...@@ -101,40 +101,40 @@
"96": { "96": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"128": { "128": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"256": { "256": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"512": { "512": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
...@@ -151,7 +151,7 @@ ...@@ -151,7 +151,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"1536": { "1536": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -173,7 +173,7 @@ ...@@ -173,7 +173,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"3072": { "3072": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -195,6 +195,6 @@ ...@@ -195,6 +195,6 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "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
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"8": {
"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
},
"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
},
"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
},
"32": {
"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
},
"48": {
"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
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4": {
"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
},
"8": {
"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": 2
},
"16": {
"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": 2
},
"24": {
"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
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"256": {
"BLOCK_SIZE_M": 64,
"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": 32,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 128,
"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
},
"1024": {
"BLOCK_SIZE_M": 128,
"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
},
"1536": {
"BLOCK_SIZE_M": 128,
"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
},
"2048": {
"BLOCK_SIZE_M": 128,
"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
},
"3072": {
"BLOCK_SIZE_M": 128,
"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
},
"4096": {
"BLOCK_SIZE_M": 128,
"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
}
}
{
"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
},
"2": {
"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
},
"4": {
"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
},
"8": {
"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
},
"16": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"24": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"32": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{ {
"1": { "1": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 2,
...@@ -12,54 +12,54 @@ ...@@ -12,54 +12,54 @@
}, },
"2": { "2": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 32, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"4": { "4": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"8": { "8": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 1,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"16": { "16": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256, "BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 4, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"24": { "24": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
"num_warps": 8, "num_warps": 1,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -68,7 +68,7 @@ ...@@ -68,7 +68,7 @@
"32": { "32": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 2, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
...@@ -78,32 +78,32 @@ ...@@ -78,32 +78,32 @@
}, },
"48": { "48": {
"BLOCK_SIZE_M": 16, "BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 1,
"num_warps": 2, "num_warps": 2,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"64": { "64": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 4, "num_warps": 4,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 2 "kpack": 1
}, },
"96": { "96": {
"BLOCK_SIZE_M": 32, "BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128, "BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 4, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
...@@ -112,18 +112,18 @@ ...@@ -112,18 +112,18 @@
"128": { "128": {
"BLOCK_SIZE_M": 64, "BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64, "BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"256": { "256": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4, "GROUP_SIZE_M": 4,
"num_warps": 8, "num_warps": 8,
"num_stages": 2, "num_stages": 2,
...@@ -140,7 +140,7 @@ ...@@ -140,7 +140,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"1024": { "1024": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -151,7 +151,7 @@ ...@@ -151,7 +151,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"1536": { "1536": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -173,7 +173,7 @@ ...@@ -173,7 +173,7 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
}, },
"3072": { "3072": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 128,
...@@ -187,7 +187,7 @@ ...@@ -187,7 +187,7 @@
"kpack": 2 "kpack": 2
}, },
"4096": { "4096": {
"BLOCK_SIZE_M": 128, "BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 128, "BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64, "BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1, "GROUP_SIZE_M": 1,
...@@ -195,6 +195,6 @@ ...@@ -195,6 +195,6 @@
"num_stages": 2, "num_stages": 2,
"waves_per_eu": 0, "waves_per_eu": 0,
"matrix_instr_nonkdim": 16, "matrix_instr_nonkdim": 16,
"kpack": 1 "kpack": 2
} }
} }
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"2": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"4": {
"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
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0
},
"24": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"32": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"48": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0
},
"96": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0
},
"256": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0
},
"512": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1024": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"1536": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"2048": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"3072": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 128,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
},
"4096": {
"BLOCK_SIZE_M": 256,
"BLOCK_SIZE_N": 256,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0
}
}
{
"1": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 1,
"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": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"4": {
"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
},
"8": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 16,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 1,
"num_warps": 1,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 1
},
"16": {
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 2,
"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": 2,
"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": 4,
"num_warps": 2,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"48": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 8,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"64": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"96": {
"BLOCK_SIZE_M": 32,
"BLOCK_SIZE_N": 32,
"BLOCK_SIZE_K": 256,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"128": {
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 4,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"256": {
"BLOCK_SIZE_M": 128,
"BLOCK_SIZE_N": 128,
"BLOCK_SIZE_K": 64,
"GROUP_SIZE_M": 1,
"num_warps": 4,
"num_stages": 2,
"waves_per_eu": 0,
"matrix_instr_nonkdim": 16,
"kpack": 2
},
"512": {
"BLOCK_SIZE_M": 128,
"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
},
"1024": {
"BLOCK_SIZE_M": 128,
"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
},
"1536": {
"BLOCK_SIZE_M": 128,
"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
},
"2048": {
"BLOCK_SIZE_M": 128,
"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
},
"3072": {
"BLOCK_SIZE_M": 128,
"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
},
"4096": {
"BLOCK_SIZE_M": 128,
"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
}
}
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