|
|
@@ -4964,6 +4964,7 @@
|
|
|
"CUDA0","CONV_TRANSPOSE_1D","ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1","support","1","yes","CUDA"
|
|
|
"CUDA0","CONV_TRANSPOSE_2D","ne_input=[3,2,3,1],ne_kernel=[2,2,1,3],stride=1","support","1","yes","CUDA"
|
|
|
"CUDA0","CONV_TRANSPOSE_2D","ne_input=[10,10,9,1],ne_kernel=[3,3,1,9],stride=2","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONV_TRANSPOSE_2D","ne_input=[129,63,35,1],ne_kernel=[3,3,48,35],stride=1","support","1","yes","CUDA"
|
|
|
"CUDA0","COUNT_EQUAL","type=f32,ne=[4,500,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","COUNT_EQUAL","type=f32,ne=[4,5000,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGMAX","type=f32,ne=[32,1,1,1]","support","1","yes","CUDA"
|
|
|
@@ -5419,17 +5420,45 @@
|
|
|
"CUDA0","CPY","type_src=f16,type_dst=f16,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","CUDA"
|
|
|
"CUDA0","CPY","type_src=f32,type_dst=f32,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","CUDA"
|
|
|
"CUDA0","CPY","type_src=bf16,type_dst=bf16,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CPY","type_src=i32,type_dst=i32,ne=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CPY","type_src=i32,type_dst=i32,ne=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","CUDA"
|
|
|
"CUDA0","CPY","type_src=f32,type_dst=f32,ne=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f32,ne=[10,10,10,1]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f32,ne=[2,1,1,1]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f32,ne=[2,1,3,5]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f32,ne=[2,3,5,7]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f16,ne=[2,1,1,1]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f16,ne=[2,1,3,5]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=f16,ne=[2,3,5,7]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=bf16,ne=[2,1,1,1]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=bf16,ne=[2,1,3,5]","support","1","yes","CUDA"
|
|
|
-"CUDA0","CONT","type=bf16,ne=[2,3,5,7]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,1,1,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,1,3,5],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,3,5,7],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[1,4,4,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[1,8,17,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[10,10,10,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,1,1,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,1,3,5],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[2,3,5,7],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[1,4,4,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[1,8,17,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f32,ne=[10,10,10,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,1,1,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,1,3,5],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,3,5,7],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[1,4,4,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[1,8,17,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[10,10,10,1],use_view_slice=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,1,1,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,1,3,5],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[2,3,5,7],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[1,4,4,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[1,8,17,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=i32,ne=[10,10,10,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[2,1,1,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[2,1,3,5],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[2,3,5,7],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[1,4,4,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[1,8,17,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=f16,ne=[10,10,10,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[2,1,1,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[2,1,3,5],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[2,3,5,7],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[1,4,4,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[1,8,17,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","CONT","type=bf16,ne=[10,10,10,1],use_view_slice=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ADD","type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1","support","1","yes","CUDA"
|
|
|
"CUDA0","SUB","type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1","support","1","yes","CUDA"
|
|
|
"CUDA0","MUL","type=f16,ne=[1,1,8,1],nr=[1,1,1,1],nf=1","support","1","yes","CUDA"
|
|
|
@@ -5655,6 +5684,7 @@
|
|
|
"CUDA0","MUL","type=f32,ne=[64,262144,1,1],nr=[1,1,1,1],nf=1","support","1","yes","CUDA"
|
|
|
"CUDA0","DIV","type=f32,ne=[64,262144,1,1],nr=[1,1,1,1],nf=1","support","1","yes","CUDA"
|
|
|
"CUDA0","ADD1","type=f32,ne=[10,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","ADD1","type=f32,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","SCALE","type=f32,ne=[10,10,10,10],scale=2.000000,bias=0.000000,inplace=0","support","1","yes","CUDA"
|
|
|
"CUDA0","SCALE","type=f32,ne=[10,10,10,10],scale=2.000000,bias=1.000000,inplace=0","support","1","yes","CUDA"
|
|
|
"CUDA0","SCALE","type=f32,ne=[10,10,10,10],scale=2.000000,bias=1.000000,inplace=1","support","1","yes","CUDA"
|
|
|
@@ -8644,9 +8674,13 @@
|
|
|
"CUDA0","CLAMP","type=f16,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","1","yes","CUDA"
|
|
|
"CUDA0","LEAKY_RELU","type=f16,ne_a=[7,1,5,3],negative_slope=0.100000","support","1","yes","CUDA"
|
|
|
"CUDA0","FLOOR","type=f16,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","FLOOR","type=f16,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","CEIL","type=f16,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CEIL","type=f16,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","ROUND","type=f16,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","ROUND","type=f16,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","TRUNC","type=f16,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","TRUNC","type=f16,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","SQR","type=f32,ne=[10,5,4,3]","support","1","yes","CUDA"
|
|
|
"CUDA0","SQRT","type=f32,ne=[10,3,3,2]","support","1","yes","CUDA"
|
|
|
"CUDA0","LOG","type=f32,ne=[10,5,4,3]","support","1","yes","CUDA"
|
|
|
@@ -8666,9 +8700,13 @@
|
|
|
"CUDA0","CLAMP","type=f32,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","1","yes","CUDA"
|
|
|
"CUDA0","LEAKY_RELU","type=f32,ne_a=[7,1,5,3],negative_slope=0.100000","support","1","yes","CUDA"
|
|
|
"CUDA0","FLOOR","type=f32,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","FLOOR","type=f32,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","CEIL","type=f32,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CEIL","type=f32,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","ROUND","type=f32,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","ROUND","type=f32,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","TRUNC","type=f32,ne=[7,1,5,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","TRUNC","type=f32,ne=[1024,1024,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","DIAG_MASK_INF","type=f32,ne=[10,10,1,1],n_past=5","support","1","yes","CUDA"
|
|
|
"CUDA0","DIAG_MASK_INF","type=f32,ne=[10,10,3,1],n_past=5","support","1","yes","CUDA"
|
|
|
"CUDA0","DIAG_MASK_INF","type=f32,ne=[10,10,3,2],n_past=5","support","1","yes","CUDA"
|
|
|
@@ -9411,18 +9449,405 @@
|
|
|
"CUDA0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","0","no","CUDA"
|
|
|
"CUDA0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","CUDA"
|
|
|
"CUDA0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","0","no","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[3,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[7,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[8,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[15,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[16,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[31,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[63,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[64,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[127,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[128,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[255,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[256,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[511,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[512,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1023,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1024,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2047,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2048,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4095,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4096,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[8191,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[8192,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[16383,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[16384,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32767,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32768,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[65535,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[65536,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[131071,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[131072,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[262143,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[262144,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[524287,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[524288,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1048575,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1048576,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[16,10,10,10],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[60,10,10,10],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1023,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1024,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1025,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2047,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2048,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2049,2,1,3],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2,8,8192,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[3,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[7,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[8,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[15,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[16,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[31,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[63,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[64,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[127,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[128,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[255,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[256,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[511,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[512,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1023,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[1024,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2047,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2048,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4095,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[4096,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[8191,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[8192,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[16383,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[16384,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
-"CUDA0","ARGSORT","type=f32,ne=[2,8,8192,1],order=0","support","1","yes","CUDA"
|
|
|
-"CUDA0","ARGSORT","type=f32,ne=[8,1,1,1],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32767,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[32768,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[65535,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[65536,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[131071,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[131072,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[262143,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[262144,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[524287,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[524288,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1048575,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1048576,1,1,1],order=0","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[16,10,10,10],order=1","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[60,10,10,10],order=1","support","1","yes","CUDA"
|
|
|
-"CUDA0","ARGSORT","type=f32,ne=[1024,1,1,1],order=1","support","1","yes","CUDA"
|
|
|
-"CUDA0","ARGSORT","type=f32,ne=[16384,1,1,1],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1023,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1024,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[1025,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2047,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2048,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARGSORT","type=f32,ne=[2049,2,1,3],order=1","support","1","yes","CUDA"
|
|
|
"CUDA0","ARGSORT","type=f32,ne=[2,8,8192,1],order=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[12,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[13,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[13,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[15,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[15,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[15,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[19,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[19,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[19,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[19,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[27,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[27,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[27,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[27,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[27,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[43,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[43,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[43,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[43,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[43,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[64,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[75,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[64,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[75,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[64,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[75,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[64,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[75,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[64,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[75,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[128,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[139,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[256,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[267,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[512,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[523,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1035,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2059,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4096,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[4107,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8192,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[8203,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16395,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32768,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[32779,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65536,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[65547,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131072,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[131083,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262144,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[262155,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=100,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=500,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=1023,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524288,1,1,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[524299,1,2,1],k=9999,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,10,10,10],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[60,10,10,10],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1023,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1025,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2047,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2049,2,1,3],k=1,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,10,10,10],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[60,10,10,10],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1023,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1025,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2047,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2049,2,1,3],k=2,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,10,10,10],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[60,10,10,10],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1023,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1025,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2047,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2049,2,1,3],k=3,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,10,10,10],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[60,10,10,10],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1023,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1025,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2047,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2049,2,1,3],k=7,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16,10,10,10],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[60,10,10,10],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1023,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1024,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[1025,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[16384,1,1,1],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2047,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2048,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
+"CUDA0","TOP_K","type=f32,ne=[2049,2,1,3],k=15,ties=0","support","0","no","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[512,512,3,2],scale_factor=2,mode=nearest,transpose=0","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[512,512,3,2],scale_factor=2,mode=nearest,transpose=1","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=nearest,flags=none","support","1","yes","CUDA"
|
|
|
@@ -9435,6 +9860,10 @@
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[512,512,3,2],scale_factor=2,mode=bicubic,transpose=1","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=bicubic,flags=none","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[5,7,11,13],ne_tgt=[2,5,7,11],mode=bicubic,flags=none","support","1","yes","CUDA"
|
|
|
+"CUDA0","UPSCALE","type=f32,ne=[512,512,3,2],scale_factor=2,mode=513,transpose=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","UPSCALE","type=f32,ne=[512,512,3,2],scale_factor=2,mode=513,transpose=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","UPSCALE","type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=bilinear,flags=none","support","1","yes","CUDA"
|
|
|
+"CUDA0","UPSCALE","type=f32,ne=[5,7,11,13],ne_tgt=[2,5,7,11],mode=bilinear,flags=none","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[2,5,7,11],ne_tgt=[5,7,11,13],mode=bilinear,flags=align_corners","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[1,4,3,2],ne_tgt=[2,8,3,2],mode=bilinear,flags=align_corners","support","1","yes","CUDA"
|
|
|
"CUDA0","UPSCALE","type=f32,ne=[4,1,3,2],ne_tgt=[1,1,3,2],mode=bilinear,flags=align_corners","support","1","yes","CUDA"
|
|
|
@@ -9463,34 +9892,59 @@
|
|
|
"CUDA0","GROUP_NORM","type=f32,ne=[64,64,320,1],num_groups=32,eps=0.000001","support","1","yes","CUDA"
|
|
|
"CUDA0","GROUP_NORM","type=f32,ne=[9,9,1280,1],num_groups=32,eps=0.000001","support","1","yes","CUDA"
|
|
|
"CUDA0","ACC","type=f32,ne_a=[256,17,1,1],ne_b=[256,16,1,1]","support","1","yes","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],pad_0=1,pad_1=1","support","1","yes","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[512,512,3,1],lp0=1,rp0=1,lp1=1,rp1=1,lp2=1,rp2=1,lp3=1,rp3=1,v=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],pad_0=1,pad_1=1,circular=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[33,17,2,1],pad_0=4,pad_1=3,circular=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,3,1],lp0=1,rp0=1,lp1=1,rp1=1,lp2=1,rp2=1,lp3=1,rp3=1,v=0,circular=0","support","1","yes","CUDA"
|
|
|
"CUDA0","PAD_REFLECT_1D","type=f32,ne_a=[512,34,2,1],pad_0=10,pad_1=9","support","1","yes","CUDA"
|
|
|
"CUDA0","PAD_REFLECT_1D","type=f32,ne_a=[3000,384,4,1],pad_0=10,pad_1=9","support","1","yes","CUDA"
|
|
|
"CUDA0","ROLL","shift0=3,shift1=-2,shift3=1,shift4=-1","support","1","yes","CUDA"
|
|
|
"CUDA0","ARANGE","type=f32,start=0.000000,stop=10.000000,step=1.000000","support","1","yes","CUDA"
|
|
|
+"CUDA0","ARANGE","type=f32,start=0.000000,stop=1048576.000000,step=1.000000","support","1","yes","CUDA"
|
|
|
"CUDA0","TIMESTEP_EMBEDDING","type=f32,ne_a=[2,1,1,1],dim=320,max_period=10000","support","1","yes","CUDA"
|
|
|
"CUDA0","LEAKY_RELU","type=f32,ne_a=[10,5,4,3],negative_slope=0.100000","support","1","yes","CUDA"
|
|
|
-"CUDA0","CUMSUM","type=f32,ne=[10,5,4,3]","support","0","no","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[10,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[127,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[128,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[128,128,4,4]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[255,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[256,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[511,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[512,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[1023,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[1024,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[2047,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[2048,5,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[242004,1,1,1]","support","1","yes","CUDA"
|
|
|
+"CUDA0","CUMSUM","type=f32,ne=[375960,1,1,1]","support","1","yes","CUDA"
|
|
|
"CUDA0","XIELU","type=f32,ne=[10,5,4,3]","support","0","no","CUDA"
|
|
|
-"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=3","support","0","no","CUDA"
|
|
|
-"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=2","support","0","no","CUDA"
|
|
|
-"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=1","support","0","no","CUDA"
|
|
|
-"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=0","support","0","no","CUDA"
|
|
|
-"CUDA0","FILL","type=f32,ne=[10,10,4,3],c=0.000000","support","0","no","CUDA"
|
|
|
-"CUDA0","FILL","type=f32,ne=[303,207,11,3],c=2.000000","support","0","no","CUDA"
|
|
|
-"CUDA0","FILL","type=f32,ne=[800,600,4,4],c=-152.000000","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[10,10,4,3],ne_rhs=[3,10,4,3]","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[11,11,1,1],ne_rhs=[5,11,1,1]","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[17,17,2,4],ne_rhs=[9,17,2,4]","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[30,30,7,1],ne_rhs=[8,30,7,1]","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[42,42,5,2],ne_rhs=[10,42,5,2]","support","0","no","CUDA"
|
|
|
-"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[64,64,2,2],ne_rhs=[10,64,2,2]","support","0","no","CUDA"
|
|
|
+"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=3","support","1","yes","CUDA"
|
|
|
+"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=2","support","1","yes","CUDA"
|
|
|
+"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","TRI","type=f32,ne=[10,10,4,3],tri_type=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","FILL","type=f32,ne=[10,10,4,3],c=0.000000","support","1","yes","CUDA"
|
|
|
+"CUDA0","FILL","type=f32,ne=[303,207,11,3],c=2.000000","support","1","yes","CUDA"
|
|
|
+"CUDA0","FILL","type=f32,ne=[800,600,4,4],c=-152.000000","support","1","yes","CUDA"
|
|
|
+"CUDA0","FILL","type=f32,ne=[2048,512,2,2],c=3.500000","support","1","yes","CUDA"
|
|
|
+"CUDA0","DIAG","type=f32,ne=[10,1,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","DIAG","type=f32,ne=[79,1,19,13]","support","1","yes","CUDA"
|
|
|
+"CUDA0","DIAG","type=f32,ne=[256,1,8,16]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[10,10,4,3],ne_rhs=[3,10,4,3]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[11,11,1,1],ne_rhs=[5,11,1,1]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[17,17,2,4],ne_rhs=[9,17,2,4]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[30,30,7,1],ne_rhs=[8,30,7,1]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[42,42,5,2],ne_rhs=[10,42,5,2]","support","1","yes","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[64,64,2,2],ne_rhs=[10,64,2,2]","support","1","yes","CUDA"
|
|
|
"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[100,100,4,4],ne_rhs=[41,100,4,4]","support","0","no","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=0","support","1","yes","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=0","support","1","yes","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=1","support","0","no","CUDA"
|
|
|
-"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=1","support","0","no","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[128,128,4,4],ne_rhs=[31,128,4,4]","support","0","no","CUDA"
|
|
|
+"CUDA0","SOLVE_TRI","type=f32,ne_lhs=[64,64,4,4],ne_rhs=[300,64,4,4]","support","0","no","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=0,circular=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=0,circular=0","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=0,circular=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=0,circular=1","support","1","yes","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=1,circular=0","support","0","no","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=1,circular=0","support","0","no","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,v=1,circular=1","support","0","no","CUDA"
|
|
|
+"CUDA0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,v=1,circular=1","support","0","no","CUDA"
|
|
|
"CUDA0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f32,permute=[0,1,2,3]","support","1","yes","CUDA"
|
|
|
"CUDA0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=f16,permute=[0,1,2,3]","support","1","yes","CUDA"
|
|
|
"CUDA0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_KV=bf16,permute=[0,1,2,3]","support","0","no","CUDA"
|