Device: NVIDIA GeForce RTX 5080
SM count: 84
Compute capability: 12.0
L2 cache size: 64.00 MiB
Global memory: 15.47 GiB
Memory bus width: 256 bits

PCI Bus ID:                 0000:01:00.0
Current GPU graphics clock: 2932 MHz
Current SM clock:           2932 MHz
Current memory clock:       14801 MHz

working_set_KB, cycles_per_dependent_load
Running working set = 4 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
4, 43.00
Running working set = 8 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
8, 43.00
Running working set = 12 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
12, 43.00
Running working set = 16 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
16, 43.00
Running working set = 20 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
20, 43.00
Running working set = 24 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
24, 43.00
Running working set = 28 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
28, 43.00
Running working set = 32 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
32, 43.00
Running working set = 36 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
36, 43.00
Running working set = 40 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
40, 43.00
Running working set = 44 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
44, 43.00
Running working set = 48 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
48, 43.00
Running working set = 52 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
52, 43.00
Running working set = 56 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
56, 43.00
Running working set = 60 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
60, 43.00
Running working set = 64 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
64, 43.00
Running working set = 68 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
68, 43.00
Running working set = 72 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
72, 43.00
Running working set = 76 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
76, 43.00
Running working set = 80 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
80, 43.00
Running working set = 84 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
84, 43.00
Running working set = 88 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
88, 43.00
Running working set = 92 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
92, 84.53
Running working set = 96 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
96, 123.81
Running working set = 100 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
100, 151.51
Running working set = 104 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
104, 176.44
Running working set = 108 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
108, 191.99
Running working set = 112 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
112, 207.09
Running working set = 116 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
116, 217.90
Running working set = 120 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
120, 229.30
Running working set = 124 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
124, 237.52
Running working set = 128 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
128, 244.07
Running working set = 132 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
132, 251.78
Running working set = 136 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
136, 257.48
Running working set = 140 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
140, 261.38
Running working set = 144 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
144, 266.83
Running working set = 148 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
148, 271.17
Running working set = 152 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
152, 275.26
Running working set = 156 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
156, 278.97
Running working set = 160 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
160, 282.36
Running working set = 164 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
164, 285.32
Running working set = 168 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
168, 288.22
Running working set = 172 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
172, 290.37
Running working set = 176 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
176, 293.53
Running working set = 180 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
180, 295.68
Running working set = 184 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
184, 297.94
Running working set = 188 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
188, 299.78
Running working set = 192 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
192, 301.70
Running working set = 196 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
196, 303.63
Running working set = 200 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
200, 304.72
Running working set = 204 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
204, 306.22
Running working set = 208 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
208, 308.19
Running working set = 212 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
212, 309.87
Running working set = 216 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
216, 310.26
Running working set = 220 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
220, 311.87
Running working set = 224 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
224, 313.07
Running working set = 228 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
228, 314.32
Running working set = 232 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
232, 314.95
Running working set = 236 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
236, 316.13
Running working set = 240 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
240, 317.45
Running working set = 244 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
244, 319.11
Running working set = 248 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
248, 319.21
Running working set = 252 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
252, 320.44
Running working set = 256 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
256, 321.80
Running working set = 320 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
320, 332.81
Running working set = 384 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
384, 339.40
Running working set = 448 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
448, 343.87
Running working set = 512 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
512, 346.80
Running working set = 576 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
576, 349.24
Running working set = 640 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
640, 351.30
Running working set = 704 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
704, 352.89
Running working set = 768 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
768, 354.13
Running working set = 832 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
832, 355.30
Running working set = 896 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
896, 356.24
Running working set = 960 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
960, 357.03
Running working set = 1024 KB, warmup_iters = 1048576, measure_iters = 1048576 ...
1024, 357.69
Running working set = 1088 KB, warmup_iters = 1114112, measure_iters = 1114112 ...
1088, 358.22
Running working set = 1152 KB, warmup_iters = 1179648, measure_iters = 1179648 ...
1152, 358.70
Running working set = 1216 KB, warmup_iters = 1245184, measure_iters = 1245184 ...
1216, 359.26
Running working set = 1280 KB, warmup_iters = 1310720, measure_iters = 1310720 ...
1280, 359.69
Running working set = 1344 KB, warmup_iters = 1376256, measure_iters = 1376256 ...
1344, 360.04
Running working set = 1408 KB, warmup_iters = 1441792, measure_iters = 1441792 ...
1408, 360.31
Running working set = 1472 KB, warmup_iters = 1507328, measure_iters = 1507328 ...
1472, 360.68
Running working set = 1536 KB, warmup_iters = 1572864, measure_iters = 1572864 ...
1536, 360.94
Running working set = 1600 KB, warmup_iters = 1638400, measure_iters = 1638400 ...
1600, 361.17
Running working set = 1664 KB, warmup_iters = 1703936, measure_iters = 1703936 ...
1664, 361.43
Running working set = 1728 KB, warmup_iters = 1769472, measure_iters = 1769472 ...
1728, 361.69
Running working set = 1792 KB, warmup_iters = 1835008, measure_iters = 1835008 ...
1792, 361.77
Running working set = 1856 KB, warmup_iters = 1900544, measure_iters = 1900544 ...
1856, 361.96
Running working set = 1920 KB, warmup_iters = 1966080, measure_iters = 1966080 ...
1920, 362.15
Running working set = 1984 KB, warmup_iters = 2031616, measure_iters = 2031616 ...
1984, 362.28
Running working set = 2048 KB, warmup_iters = 2097152, measure_iters = 2097152 ...
2048, 362.42
Running working set = 2112 KB, warmup_iters = 2162688, measure_iters = 2162688 ...
2112, 362.51
Running working set = 2176 KB, warmup_iters = 2228224, measure_iters = 2228224 ...
2176, 362.86
Running working set = 2240 KB, warmup_iters = 2293760, measure_iters = 2293760 ...
2240, 362.79
Running working set = 2304 KB, warmup_iters = 2359296, measure_iters = 2359296 ...
2304, 362.90
Running working set = 2368 KB, warmup_iters = 2424832, measure_iters = 2424832 ...
2368, 363.06
Running working set = 2432 KB, warmup_iters = 2490368, measure_iters = 2490368 ...
2432, 363.10
Running working set = 2496 KB, warmup_iters = 2555904, measure_iters = 2555904 ...
2496, 363.27
Running working set = 2560 KB, warmup_iters = 2621440, measure_iters = 2621440 ...
2560, 363.32
Running working set = 2624 KB, warmup_iters = 2686976, measure_iters = 2686976 ...
2624, 363.37
Running working set = 2688 KB, warmup_iters = 2752512, measure_iters = 2752512 ...
2688, 363.47
Running working set = 2752 KB, warmup_iters = 2818048, measure_iters = 2818048 ...
2752, 363.53
Running working set = 2816 KB, warmup_iters = 2883584, measure_iters = 2883584 ...
2816, 363.60
Running working set = 2880 KB, warmup_iters = 2949120, measure_iters = 2949120 ...
2880, 363.81
Running working set = 2944 KB, warmup_iters = 3014656, measure_iters = 3014656 ...
2944, 363.78
Running working set = 3008 KB, warmup_iters = 3080192, measure_iters = 3080192 ...
3008, 363.79
Running working set = 3072 KB, warmup_iters = 3145728, measure_iters = 3145728 ...
3072, 363.84
Running working set = 3136 KB, warmup_iters = 3211264, measure_iters = 3211264 ...
3136, 363.88
Running working set = 3200 KB, warmup_iters = 3276800, measure_iters = 3276800 ...
3200, 363.94
Running working set = 3264 KB, warmup_iters = 3342336, measure_iters = 3342336 ...
3264, 364.01
Running working set = 3328 KB, warmup_iters = 3407872, measure_iters = 3407872 ...
3328, 364.04
Running working set = 3392 KB, warmup_iters = 3473408, measure_iters = 3473408 ...
3392, 364.13
Running working set = 3456 KB, warmup_iters = 3538944, measure_iters = 3538944 ...
3456, 364.18
Running working set = 3520 KB, warmup_iters = 3604480, measure_iters = 3604480 ...
3520, 364.21
Running working set = 3584 KB, warmup_iters = 3670016, measure_iters = 3670016 ...
3584, 364.25
Running working set = 3648 KB, warmup_iters = 3735552, measure_iters = 3735552 ...
3648, 364.30
Running working set = 3712 KB, warmup_iters = 3801088, measure_iters = 3801088 ...
3712, 364.30
Running working set = 3776 KB, warmup_iters = 3866624, measure_iters = 3866624 ...
3776, 364.32
Running working set = 3840 KB, warmup_iters = 3932160, measure_iters = 3932160 ...
3840, 364.36
Running working set = 3904 KB, warmup_iters = 3997696, measure_iters = 3997696 ...
3904, 364.50
Running working set = 3968 KB, warmup_iters = 4063232, measure_iters = 4063232 ...
3968, 364.47
Running working set = 4032 KB, warmup_iters = 4128768, measure_iters = 4128768 ...
4032, 364.48
Running working set = 4096 KB, warmup_iters = 4194304, measure_iters = 4194304 ...
4096, 364.51
Running working set = 5120 KB, warmup_iters = 5242880, measure_iters = 5242880 ...
5120, 364.95
Running working set = 6144 KB, warmup_iters = 6291456, measure_iters = 6291456 ...
6144, 365.19
Running working set = 7168 KB, warmup_iters = 7340032, measure_iters = 7340032 ...
7168, 365.43
Running working set = 8192 KB, warmup_iters = 8388608, measure_iters = 8388608 ...
8192, 365.51
Running working set = 9216 KB, warmup_iters = 9437184, measure_iters = 9437184 ...
9216, 365.61
Running working set = 10240 KB, warmup_iters = 10485760, measure_iters = 10485760 ...
10240, 365.72
Running working set = 11264 KB, warmup_iters = 11534336, measure_iters = 11534336 ...
11264, 365.75
Running working set = 12288 KB, warmup_iters = 12582912, measure_iters = 12582912 ...
12288, 365.80
Running working set = 13312 KB, warmup_iters = 13631488, measure_iters = 13631488 ...
13312, 365.84
Running working set = 14336 KB, warmup_iters = 14680064, measure_iters = 14680064 ...
14336, 365.87
Running working set = 15360 KB, warmup_iters = 15728640, measure_iters = 15728640 ...
15360, 365.93
Running working set = 16384 KB, warmup_iters = 16777216, measure_iters = 16777216 ...
16384, 365.94
Running working set = 17408 KB, warmup_iters = 17825792, measure_iters = 17825792 ...
17408, 365.94
Running working set = 18432 KB, warmup_iters = 18874368, measure_iters = 18874368 ...
18432, 365.98
Running working set = 19456 KB, warmup_iters = 19922944, measure_iters = 19922944 ...
19456, 366.01
Running working set = 20480 KB, warmup_iters = 20971520, measure_iters = 20971520 ...
20480, 366.01
Running working set = 21504 KB, warmup_iters = 22020096, measure_iters = 22020096 ...
21504, 366.04
Running working set = 22528 KB, warmup_iters = 23068672, measure_iters = 23068672 ...
22528, 366.06
Running working set = 23552 KB, warmup_iters = 24117248, measure_iters = 24117248 ...
23552, 366.08
Running working set = 24576 KB, warmup_iters = 25165824, measure_iters = 25165824 ...
24576, 366.09
Running working set = 25600 KB, warmup_iters = 26214400, measure_iters = 26214400 ...
25600, 366.11
Running working set = 26624 KB, warmup_iters = 27262976, measure_iters = 27262976 ...
26624, 366.11
Running working set = 27648 KB, warmup_iters = 28311552, measure_iters = 28311552 ...
27648, 366.11
Running working set = 28672 KB, warmup_iters = 29360128, measure_iters = 29360128 ...
28672, 366.12
Running working set = 29696 KB, warmup_iters = 30408704, measure_iters = 30408704 ...
29696, 366.14
Running working set = 30720 KB, warmup_iters = 31457280, measure_iters = 31457280 ...
30720, 366.15
Running working set = 31744 KB, warmup_iters = 32505856, measure_iters = 32505856 ...
31744, 366.15
Running working set = 32768 KB, warmup_iters = 33554432, measure_iters = 33554432 ...
32768, 366.15
Running working set = 36864 KB, warmup_iters = 37748736, measure_iters = 37748736 ...
36864, 366.18
Running working set = 40960 KB, warmup_iters = 41943040, measure_iters = 41943040 ...
40960, 366.18
Running working set = 45056 KB, warmup_iters = 46137344, measure_iters = 46137344 ...
45056, 366.49
Running working set = 49152 KB, warmup_iters = 50331648, measure_iters = 50331648 ...
49152, 366.76
Running working set = 53248 KB, warmup_iters = 54525952, measure_iters = 54525952 ...
53248, 366.88
Running working set = 57344 KB, warmup_iters = 58720256, measure_iters = 58720256 ...
57344, 367.41
Running working set = 61440 KB, warmup_iters = 62914560, measure_iters = 62914560 ...
61440, 373.69
Running working set = 65536 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
65536, 410.09
Running working set = 69632 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
69632, 507.70
Running working set = 73728 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
73728, 583.84
Running working set = 77824 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
77824, 638.27
Running working set = 81920 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
81920, 676.72
Running working set = 86016 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
86016, 704.44
Running working set = 90112 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
90112, 727.30
Running working set = 94208 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
94208, 746.01
Running working set = 98304 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
98304, 761.23
Running working set = 102400 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
102400, 774.71
Running working set = 106496 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
106496, 785.54
Running working set = 110592 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
110592, 791.76
Running working set = 114688 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
114688, 799.89
Running working set = 118784 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
118784, 807.13
Running working set = 122880 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
122880, 813.48
Running working set = 126976 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
126976, 819.06
Running working set = 131072 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
131072, 824.30
Running working set = 163840 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
163840, 851.62
Running working set = 229376 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
229376, 876.97
Running working set = 294912 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
294912, 889.55
Running working set = 360448 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
360448, 897.38
Running working set = 425984 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
425984, 903.74
Running working set = 491520 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
491520, 909.81
Running working set = 557056 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
557056, 911.95
Running working set = 622592 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
622592, 914.11
Running working set = 688128 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
688128, 915.84
Running working set = 753664 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
753664, 917.81
Running working set = 819200 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
819200, 914.92
Running working set = 884736 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
884736, 915.80
Running working set = 950272 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
950272, 916.55
Running working set = 1015808 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1015808, 917.21
Running working set = 1081344 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1081344, 917.79
Running working set = 1146880 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1146880, 918.46
Running working set = 1212416 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1212416, 919.25
Running working set = 1277952 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1277952, 919.56
Running working set = 1343488 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1343488, 919.55
Running working set = 1409024 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1409024, 924.04
Running working set = 1474560 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1474560, 923.92
Running working set = 1540096 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1540096, 924.15
Running working set = 1605632 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1605632, 924.87
Running working set = 1671168 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1671168, 923.56
Running working set = 1736704 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1736704, 921.08
Running working set = 1802240 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1802240, 921.24
Running working set = 1867776 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1867776, 921.42
Running working set = 1933312 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1933312, 921.57
Running working set = 1998848 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
1998848, 922.12
Running working set = 2064384 KB, warmup_iters = 67108864, measure_iters = 67108864 ...
2064384, 922.25
