@@ -154,18 +154,18 @@ auto _CATALOG_ = kcatalog::toArray({
154
154
{{'E', "gemm", {"F", "B", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1, 1}, "Ixy"}, "sB16 sB16 aB wg 4x16 cab4 ks32 af dw vav bo bk0 sn grf256 pab sys l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 131072, 16777216}, {8192, 8192, 16777216}, {32, 8, 32}, {4, 16, 1}, 1, (WGType) 1, 257, 65536, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {540457, 1.10675e+06, 0, 0, 0, 0, 5.61877, 5.78531, 5.50943, 14.7763, 0.0373088, 0.0373088, 0, 1, 1.21298, 1.20167, -5.60976e-15}}},
155
155
{{'E', "gemm", {"F", "B", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, 8, -1}, {-1, -1, -1}, {-1, 8, -1}, {4, 4, 1}, "xyz"}, "sB4x2 sS2 sB wg 4x2x8 akr fg 0.25 kc2 nse sr sb32 bk0 bm0 pab", {8, (LoopType) 0, 128, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {64, 4, 4}, {4, 2, 8}, 1, (WGType) 0, 262917, 0, 8192, {4, 4, 4}, {false, false, false}}, {'W', 1, {256}}},
156
156
{{'E', "gemm", {"F", "B", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1, 1}, "ixy"}, "sB2 sB2 aB wg 4x8 kc2 cab4 ks8 nse bo sr bk0 sn l4 pab", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 262144, 16777216}, {524288, 262144, 16777216}, {32, 16, 8}, {4, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {1, 2, 4}, {false, false, true}}, {'W', 1, {512}}},
157
- {{'E', "gemm", {"F", "B", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1 , 1}, "I"}, "sB32 sB32 aB wg 2x8 cab4 ks64 af dw vav bo bk0 sm sn grf256 pab sys l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {262144, 65536, 16777216}, {8192, 8192, 16777216}, {16, 4, 64}, {2, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.27535e+06, 215187, 0, 0, 0, 0, 4.64559, 4.65327, 3.47044, 9.89232, 0.105235, 0.0510608, 0.0580013, 1, 1.20879, 1.2012, -2.49667e-15}}},
158
- {{'E', "gemm", {"F", "B", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, 16, -1}, {-1, -1, -1}, {-1, 16, -1}, {1, 1 , 1}, "xyI"}, "sB64 sS16 aS wg 2x1x16 ikr af vav sr bk0 bm0 sys pab grf256 l4", {8, (LoopType) 0, 256, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {8, 16, 64}, {2, 1, 16}, 1, (WGType) 0, 4357, 0, 1024, {1 , 2, 4}, {false, false, true}}, {'W', 1, {128}}},
157
+ {{'E', "gemm", {"F", "B", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {2, 2 , 1}, "I"}, "sB32 sB32 aB wg 2x8 cab4 ks64 af dw vav bo bk0 sm sn grf256 pab sys l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {262144, 65536, 16777216}, {8192, 8192, 16777216}, {16, 4, 64}, {2, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.27535e+06, 215187, 0, 0, 0, 0, 4.64559, 4.65327, 3.47044, 9.89232, 0.105235, 0.0510608, 0.0580013, 1, 1.20879, 1.2012, -2.49667e-15}}},
158
+ {{'E', "gemm", {"F", "B", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, 16, -1}, {-1, -1, -1}, {-1, 16, -1}, {2, 2 , 1}, "xyI"}, "sB64 sS16 aS wg 2x1x16 ikr af vav sr bk0 bm0 sys pab grf256 l4", {8, (LoopType) 0, 256, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {8, 16, 64}, {2, 1, 16}, 1, (WGType) 0, 4357, 0, 1024, {2 , 2, 4}, {false, false, true}}, {'W', 1, {128}}},
159
159
{{'E', "gemm", {"F", "B", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1, 1}, "ixy"}, "sB4 sB4 aB wg 4x8 kc4 cab4 ks8 nse bo sr bk0 sm sn l4 pab", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 262144, 16777216}, {524288, 262144, 16777216}, {32, 16, 8}, {4, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {1, 2, 4}, {false, false, true}}, {'W', 1, {512}}},
160
160
{{'E', "gemm", {"F", "H", "S"}, {"A", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 4, 1}, "xyzI"}, "sB32 sB32 sB wg 2x1x16 akr fg 0.25 nse sr sb32 bk0 bm0 pab sys", {8, (LoopType) 0, 128, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {16, 4, 32}, {2, 1, 16}, 1, (WGType) 0, 262917, 0, 512, {8, 4, 4}, {false, false, false}}, {'W', 1, {64}}},
161
161
{{'E', "gemm", {"F", "H", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1, 1}, "Ixy"}, "sB16 sB16 aB wg 8x8 cab4 ks16 af dw vav bo bk0 sn grf256 sys l4 pab sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 524288, 16777216}, {8192, 8192, 16777216}, {32, 32, 16}, {8, 8, 1}, 1, (WGType) 1, 257, 65536, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {568500, 1.28115e+06, 0, 0, 0, 0, 5.43293, 5.22848, 6.20609, 17.6026, 0.0197921, 0.0197921, 0, 1, 1.32313, 1.19039, 7.17197e-13}}},
162
162
{{'E', "gemm", {"F", "H", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, 4, -1}, {-1, -1, -1}, {-1, 4, -1}, {4, 4, 1}, "xyz"}, "sB4x2 sS8 sB wg 2x1x16 akr fg 0.5 kc4 nse sr sb32 bk0 bm0 grf256 pab", {8, (LoopType) 0, 256, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {64, 4, 8}, {2, 1, 16}, 1, (WGType) 0, 525061, 0, 2048, {4, 4, 4}, {false, false, false}}, {'W', 1, {256}}},
163
163
{{'E', "gemm", {"F", "H", "S"}, {"N", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1, 1}, "ixy"}, "sB2x2 sB2x2 aB wg 4x8 kc2 cab4 ks8 nse bo sr bk0 sn l4 pab grf256", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 262144, 16777216}, {524288, 262144, 16777216}, {32, 16, 8}, {4, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {1, 2, 4}, {false, false, true}}, {'W', 1, {512}}},
164
- {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1 , 1}, "I"}, "sB32 sB64 aB wg 8x4 cab4 ks64 af dw vav bo bk0 sm sn sys pab l4 sr", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {131072, 131072, 16777216}, {8192, 8192, 16777216}, {8, 8, 64}, {8, 4, 1}, 1, (WGType) 1, 257, 49152, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.06234e+06, 445401, 0, 0, 0, 0, 4.62244, 5.31323, 3.78655, 11.4316, 0.08593, 0.0721937, 0.0244972, 1, 1.21089, 1.20155, -5.01322e-15}}},
165
- {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1 , 1}, "I"}, "sB32 sB32 aB wg 4x4 cab3 ks64 af dw vav bo bk0 sm sn grf256 sys pab l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {262144, 65536, 16777216}, {8192, 8192, 16777216}, {16, 4, 64}, {4, 4, 1}, 1, (WGType) 1, 257, 30720, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.24598e+06, 199092, 0, 0, 0, 0, 5.11406, 6.54063, 3.6868, 10.138, 0.114685, 0.0491769, 0.0713602, 0.902881, 1.20724, 1.20086, 6.44189e-15}}},
166
- {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1 , 1}, "I"}, "sB32 sB16 aB wg 2x4x4 kr cab4 ks32 af dw vav bo bk0 sm sn grf256 sys pab l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 2}, {262144, 131072, 16777216}, {8192, 8192, 16777216}, {16, 8, 32}, {2, 4, 4}, 1, (WGType) 1, 261, 65536, 16384, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.00833e+06, 472991, 67249.4, 65461, 0, 0, 5.08333, 5.12749, 4.89837, 12.0468, 0.0787666, 0.065148, 0.0481217, 1, 1.20614, 1.20116, 2.71563e-15}}},
164
+ {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {2, 2 , 1}, "I"}, "sB32 sB64 aB wg 8x4 cab4 ks64 af dw vav bo bk0 sm sn sys pab l4 sr", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {131072, 131072, 16777216}, {8192, 8192, 16777216}, {8, 8, 64}, {8, 4, 1}, 1, (WGType) 1, 257, 49152, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.06234e+06, 445401, 0, 0, 0, 0, 4.62244, 5.31323, 3.78655, 11.4316, 0.08593, 0.0721937, 0.0244972, 1, 1.21089, 1.20155, -5.01322e-15}}},
165
+ {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {2, 2 , 1}, "I"}, "sB32 sB32 aB wg 4x4 cab3 ks64 af dw vav bo bk0 sm sn grf256 sys pab l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {262144, 65536, 16777216}, {8192, 8192, 16777216}, {16, 4, 64}, {4, 4, 1}, 1, (WGType) 1, 257, 30720, 0, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.24598e+06, 199092, 0, 0, 0, 0, 5.11406, 6.54063, 3.6868, 10.138, 0.114685, 0.0491769, 0.0713602, 0.902881, 1.20724, 1.20086, 6.44189e-15}}},
166
+ {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {2, 2 , 1}, "I"}, "sB32 sB16 aB wg 2x4x4 kr cab4 ks32 af dw vav bo bk0 sm sn grf256 sys pab l4 sr", {8, (LoopType) 0, 256, {(LoopType) 128, (LoopType) 255, (LoopType) 2}, {262144, 131072, 16777216}, {8192, 8192, 16777216}, {16, 8, 32}, {2, 4, 4}, 1, (WGType) 1, 261, 65536, 16384, {2, 2, 4}, {false, false, true}}, {'E', 17, {1.00833e+06, 472991, 67249.4, 65461, 0, 0, 5.08333, 5.12749, 4.89837, 12.0468, 0.0787666, 0.065148, 0.0481217, 1, 1.20614, 1.20116, 2.71563e-15}}},
167
167
{{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, 2, -1}, {-1, 8, -1}, {-1, 2, -1}, {-1, 8, -1}, {4, 4, 1}, "Iqxy"}, "sB64 sS16 aS wg 2x1x16 ikr af vav sr bk0 bm0 sys pab grf256", {8, (LoopType) 0, 256, {(LoopType) 0, (LoopType) 1, (LoopType) 2}, {16777216, 8192, 16777216}, {8192, 8192, 16777216}, {16, 8, 64}, {2, 1, 16}, 1, (WGType) 0, 4357, 0, 1024, {4, 4, 4}, {false, false, true}}, {'W', 1, {128}}},
168
- {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 1 , 1}, "ixy"}, "sB4 sB4 aB wg 4x8 kc4 cab4 ks8 nse bo sr bk0 sm sn l4 pab", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 262144, 16777216}, {524288, 262144, 16777216}, {32, 16, 8}, {4, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {1, 2, 4}, {false, false, true}}, {'W', 1, {512}}},
168
+ {{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {-1, -1, -1}, {1, 2 , 1}, "ixy"}, "sB4 sB4 aB wg 4x8 kc4 cab4 ks8 nse bo sr bk0 sm sn l4 pab", {8, (LoopType) 0, 128, {(LoopType) 128, (LoopType) 255, (LoopType) 255}, {524288, 262144, 16777216}, {524288, 262144, 16777216}, {32, 16, 8}, {4, 8, 1}, 1, (WGType) 1, 257, 32768, 0, {1, 2, 4}, {false, false, true}}, {'W', 1, {512}}},
169
169
{{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {-1, 1, -1}, {512, 1, -1}, {-1, 1, -1}, {512, 1, -1}, {4, 4, 1}, ""}, "aB128x2 aB64x2 aB wg 2x1x8 ikr ar sb128 bk0 dot wt", {8, (LoopType) 0, 128, {(LoopType) 160, (LoopType) 255, (LoopType) 2}, {16384, 16384, 16777216}, {16384, 16384, 16777216}, {1, 1, 128}, {2, 1, 8}, 1, (WGType) 0, 4198661, 0, 64, {4, 4, 4}, {true, true, true}}, {'W', 1, {1}}},
170
170
{{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {513, 1, -1}, {1024, 1, -1}, {513, 1, -1}, {1024, 1, -1}, {4, 4, 1}, ""}, "aB64 aB32x2 aB wg 2x1x8 ikr nse hi ar sb64 bk0 dot wt", {8, (LoopType) 0, 128, {(LoopType) 144, (LoopType) 255, (LoopType) 2}, {65536, 16384, 16777216}, {65536, 16384, 16777216}, {4, 1, 64}, {2, 1, 8}, 1, (WGType) 0, 4198661, 0, 64, {4, 4, 4}, {true, true, true}}, {'W', 1, {4}}},
171
171
{{'E', "gemm", {"F", "H", "S"}, {"T", "N", "N"}}, {-1, -1, {4097, 1, 2049}, {-1, 1, -1}, {4097, 1, 2049}, {-1, 1, -1}, {4, 4, 1}, ""}, "aB16 aB128 aB wg 2x1x16 ikr nse hi ar sb128 bk0 dot wt", {8, (LoopType) 0, 128, {(LoopType) 144, (LoopType) 255, (LoopType) 2}, {65536, 16384, 16777216}, {65536, 16384, 16777216}, {4, 1, 128}, {2, 1, 16}, 1, (WGType) 0, 4198661, 0, 64, {4, 4, 4}, {true, true, true}}, {'W', 1, {4}}},
0 commit comments