Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add b200 tunings for radix_sort.keys #3611

Merged
merged 1 commit into from
Jan 31, 2025

Conversation

bernhardmgruber
Copy link
Contributor

@bernhardmgruber bernhardmgruber commented Jan 30, 2025

Benchmark main vs. this PR on B200:

|  T{ct}  |  OffsetT{ct}  |  Elements{io}  |  Entropy  |   Ref Time |   Ref Noise |   Cmp Time |   Cmp Noise |        Diff |   %Diff |  Status  |
|---------|---------------|----------------|-----------|------------|-------------|------------|-------------|-------------|---------|----------|
|   I8    |      I32      |      2^16      |     1     |  29.703 us |       3.34% |  29.690 us |       3.07% |   -0.012 us |  -0.04% |   SAME   |
|   I8    |      I32      |      2^20      |     1     |  37.131 us |       2.06% |  37.431 us |       2.39% |    0.300 us |   0.81% |   SAME   |
|   I8    |      I32      |      2^24      |     1     | 125.236 us |       1.18% | 125.268 us |       1.05% |    0.032 us |   0.03% |   SAME   |
|   I8    |      I32      |      2^28      |     1     |   1.313 ms |       0.34% |   1.313 ms |       0.23% |   -0.056 us |  -0.00% |   SAME   |
|   I8    |      I32      |      2^16      |   0.544   |  30.981 us |       4.27% |  31.080 us |       4.26% |    0.099 us |   0.32% |   SAME   |
|   I8    |      I32      |      2^20      |   0.544   |  38.347 us |       3.17% |  38.302 us |       3.20% |   -0.045 us |  -0.12% |   SAME   |
|   I8    |      I32      |      2^24      |   0.544   | 128.380 us |       1.31% | 128.470 us |       1.23% |    0.089 us |   0.07% |   SAME   |
|   I8    |      I32      |      2^28      |   0.544   |   1.331 ms |       0.24% |   1.332 ms |       0.24% |    0.795 us |   0.06% |   SAME   |
|   I8    |      I32      |      2^16      |   0.201   |  30.493 us |       3.77% |  30.384 us |       3.71% |   -0.109 us |  -0.36% |   SAME   |
|   I8    |      I32      |      2^20      |   0.201   |  36.381 us |       2.83% |  36.410 us |       2.90% |    0.029 us |   0.08% |   SAME   |
|   I8    |      I32      |      2^24      |   0.201   | 120.419 us |       1.08% | 120.381 us |       1.04% |   -0.038 us |  -0.03% |   SAME   |
|   I8    |      I32      |      2^28      |   0.201   |   1.255 ms |       0.35% |   1.255 ms |       0.33% |    0.228 us |   0.02% |   SAME   |
|   I8    |      I64      |      2^16      |     1     |  30.192 us |       3.85% |  30.284 us |       4.10% |    0.092 us |   0.30% |   SAME   |
|   I8    |      I64      |      2^20      |     1     |  37.734 us |       2.06% |  37.718 us |       2.00% |   -0.016 us |  -0.04% |   SAME   |
|   I8    |      I64      |      2^24      |     1     | 121.794 us |       0.76% | 121.915 us |       0.72% |    0.121 us |   0.10% |   SAME   |
|   I8    |      I64      |      2^28      |     1     |   1.323 ms |       0.25% |   1.323 ms |       0.26% |    0.112 us |   0.01% |   SAME   |
|   I8    |      I64      |      2^16      |   0.544   |  30.221 us |       3.87% |  30.213 us |       3.76% |   -0.008 us |  -0.03% |   SAME   |
|   I8    |      I64      |      2^20      |   0.544   |  38.073 us |       2.74% |  38.049 us |       2.79% |   -0.023 us |  -0.06% |   SAME   |
|   I8    |      I64      |      2^24      |   0.544   | 123.909 us |       1.07% | 123.906 us |       1.06% |   -0.003 us |  -0.00% |   SAME   |
|   I8    |      I64      |      2^28      |   0.544   |   1.342 ms |       0.26% |   1.342 ms |       0.26% |    0.293 us |   0.02% |   SAME   |
|   I8    |      I64      |      2^16      |   0.201   |  29.828 us |       3.18% |  29.791 us |       3.14% |   -0.038 us |  -0.13% |   SAME   |
|   I8    |      I64      |      2^20      |   0.201   |  36.729 us |       3.22% |  36.898 us |       3.45% |    0.169 us |   0.46% |   SAME   |
|   I8    |      I64      |      2^24      |   0.201   | 116.701 us |       1.09% | 116.717 us |       1.11% |    0.016 us |   0.01% |   SAME   |
|   I8    |      I64      |      2^28      |   0.201   |   1.263 ms |       0.47% |   1.263 ms |       0.48% |    0.433 us |   0.03% |   SAME   |
|   I16   |      I32      |      2^16      |     1     |  46.312 us |       1.67% |  46.440 us |       1.91% |    0.128 us |   0.28% |   SAME   |
|   I16   |      I32      |      2^20      |     1     |  58.665 us |       1.55% |  57.305 us |       2.02% |   -1.361 us |  -2.32% |   FAST   |
|   I16   |      I32      |      2^24      |     1     | 214.122 us |       0.28% | 212.096 us |       0.25% |   -2.026 us |  -0.95% |   FAST   |
|   I16   |      I32      |      2^28      |     1     |   2.590 ms |       0.07% |   2.543 ms |       0.10% |  -46.739 us |  -1.80% |   FAST   |
|   I16   |      I32      |      2^16      |   0.544   |  46.111 us |       1.33% |  46.072 us |       1.40% |   -0.039 us |  -0.08% |   SAME   |
|   I16   |      I32      |      2^20      |   0.544   |  60.360 us |       1.29% |  58.758 us |       1.67% |   -1.601 us |  -2.65% |   FAST   |
|   I16   |      I32      |      2^24      |   0.544   | 218.858 us |       0.60% | 216.667 us |       0.53% |   -2.191 us |  -1.00% |   FAST   |
|   I16   |      I32      |      2^28      |   0.544   |   2.643 ms |       0.08% |   2.598 ms |       0.10% |  -45.112 us |  -1.71% |   FAST   |
|   I16   |      I32      |      2^16      |   0.201   |  46.046 us |       1.46% |  45.983 us |       1.51% |   -0.063 us |  -0.14% |   SAME   |
|   I16   |      I32      |      2^20      |   0.201   |  56.392 us |       1.18% |  56.520 us |       1.23% |    0.128 us |   0.23% |   SAME   |
|   I16   |      I32      |      2^24      |   0.201   | 205.208 us |       0.68% | 202.913 us |       0.53% |   -2.295 us |  -1.12% |   FAST   |
|   I16   |      I32      |      2^28      |   0.201   |   2.474 ms |       0.11% |   2.426 ms |       0.14% |  -48.148 us |  -1.95% |   FAST   |
|   I16   |      I64      |      2^16      |     1     |  45.956 us |       1.40% |  45.609 us |       2.16% |   -0.346 us |  -0.75% |   SAME   |
|   I16   |      I64      |      2^20      |     1     |  58.744 us |       1.94% |  56.827 us |       1.49% |   -1.916 us |  -3.26% |   FAST   |
|   I16   |      I64      |      2^24      |     1     | 213.755 us |       0.46% | 207.097 us |       0.55% |   -6.658 us |  -3.11% |   FAST   |
|   I16   |      I64      |      2^28      |     1     |   2.611 ms |       0.24% |   2.469 ms |       0.20% | -141.897 us |  -5.43% |   FAST   |
|   I16   |      I64      |      2^16      |   0.544   |  45.960 us |       1.43% |  45.668 us |       2.11% |   -0.292 us |  -0.64% |   SAME   |
|   I16   |      I64      |      2^20      |   0.544   |  59.277 us |       2.12% |  57.677 us |       1.90% |   -1.600 us |  -2.70% |   FAST   |
|   I16   |      I64      |      2^24      |   0.544   | 216.178 us |       0.29% | 208.850 us |       0.54% |   -7.328 us |  -3.39% |   FAST   |
|   I16   |      I64      |      2^28      |   0.544   |   2.666 ms |       0.24% |   2.525 ms |       0.17% | -140.690 us |  -5.28% |   FAST   |
|   I16   |      I64      |      2^16      |   0.201   |  46.014 us |       1.30% |  46.025 us |       1.51% |    0.011 us |   0.02% |   SAME   |
|   I16   |      I64      |      2^20      |   0.201   |  57.305 us |       1.97% |  56.581 us |       0.99% |   -0.723 us |  -1.26% |   FAST   |
|   I16   |      I64      |      2^24      |   0.201   | 204.013 us |       0.38% | 199.969 us |       0.36% |   -4.044 us |  -1.98% |   FAST   |
|   I16   |      I64      |      2^28      |   0.201   |   2.498 ms |       0.32% |   2.366 ms |       0.18% | -131.878 us |  -5.28% |   FAST   |
|   I32   |      I32      |      2^16      |     1     |  75.642 us |       0.99% |  75.400 us |       1.08% |   -0.242 us |  -0.32% |   SAME   |
|   I32   |      I32      |      2^20      |     1     |  96.329 us |       1.08% |  96.170 us |       1.10% |   -0.159 us |  -0.17% |   SAME   |
|   I32   |      I32      |      2^24      |     1     | 391.202 us |       0.40% | 390.648 us |       0.39% |   -0.554 us |  -0.14% |   SAME   |
|   I32   |      I32      |      2^28      |     1     |   4.930 ms |       0.13% |   4.928 ms |       0.13% |   -2.159 us |  -0.04% |   SAME   |
|   I32   |      I32      |      2^16      |   0.544   |  75.750 us |       0.83% |  75.629 us |       0.85% |   -0.120 us |  -0.16% |   SAME   |
|   I32   |      I32      |      2^20      |   0.544   |  96.528 us |       0.81% |  96.477 us |       0.88% |   -0.051 us |  -0.05% |   SAME   |
|   I32   |      I32      |      2^24      |   0.544   | 397.930 us |       0.30% | 396.348 us |       0.35% |   -1.582 us |  -0.40% |   FAST   |
|   I32   |      I32      |      2^28      |   0.544   |   5.080 ms |       0.08% |   5.079 ms |       0.08% |   -0.970 us |  -0.02% |   SAME   |
|   I32   |      I32      |      2^16      |   0.201   |  75.733 us |       0.87% |  75.481 us |       1.04% |   -0.252 us |  -0.33% |   SAME   |
|   I32   |      I32      |      2^20      |   0.201   |  94.477 us |       0.94% |  94.311 us |       0.96% |   -0.166 us |  -0.18% |   SAME   |
|   I32   |      I32      |      2^24      |   0.201   | 379.625 us |       0.41% | 378.190 us |       0.37% |   -1.435 us |  -0.38% |   FAST   |
|   I32   |      I32      |      2^28      |   0.201   |   4.730 ms |       0.07% |   4.729 ms |       0.06% |   -0.784 us |  -0.02% |   SAME   |
|   I32   |      I64      |      2^16      |     1     |  77.417 us |       1.03% |  77.530 us |       1.00% |    0.113 us |   0.15% |   SAME   |
|   I32   |      I64      |      2^20      |     1     |  97.949 us |       0.98% |  97.926 us |       0.90% |   -0.023 us |  -0.02% |   SAME   |
|   I32   |      I64      |      2^24      |     1     | 412.331 us |       0.41% | 412.399 us |       0.39% |    0.068 us |   0.02% |   SAME   |
|   I32   |      I64      |      2^28      |     1     |   5.096 ms |       0.06% |   5.096 ms |       0.06% |    0.388 us |   0.01% |   SAME   |
|   I32   |      I64      |      2^16      |   0.544   |  77.560 us |       0.91% |  77.509 us |       0.94% |   -0.051 us |  -0.07% |   SAME   |
|   I32   |      I64      |      2^20      |   0.544   |  97.864 us |       1.03% |  97.927 us |       0.99% |    0.062 us |   0.06% |   SAME   |
|   I32   |      I64      |      2^24      |   0.544   | 419.451 us |       0.36% | 419.405 us |       0.36% |   -0.046 us |  -0.01% |   SAME   |
|   I32   |      I64      |      2^28      |   0.544   |   5.234 ms |       0.14% |   5.235 ms |       0.13% |    0.813 us |   0.02% |   SAME   |
|   I32   |      I64      |      2^16      |   0.201   |  77.441 us |       1.02% |  77.517 us |       1.12% |    0.077 us |   0.10% |   SAME   |
|   I32   |      I64      |      2^20      |   0.201   |  95.870 us |       0.97% |  95.935 us |       0.94% |    0.066 us |   0.07% |   SAME   |
|   I32   |      I64      |      2^24      |   0.201   | 393.673 us |       0.44% | 393.643 us |       0.50% |   -0.030 us |  -0.01% |   SAME   |
|   I32   |      I64      |      2^28      |   0.201   |   4.891 ms |       0.10% |   4.891 ms |       0.10% |   -0.040 us |  -0.00% |   SAME   |
|   I64   |      I32      |      2^16      |     1     | 132.681 us |       0.62% | 132.636 us |       0.56% |   -0.046 us |  -0.03% |   SAME   |
|   I64   |      I32      |      2^20      |     1     | 201.175 us |       0.65% | 201.243 us |       0.64% |    0.069 us |   0.03% |   SAME   |
|   I64   |      I32      |      2^24      |     1     |   1.436 ms |       0.19% |   1.436 ms |       0.20% |    0.140 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^28      |     1     |  21.058 ms |       0.21% |  21.059 ms |       0.19% |    1.666 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^16      |   0.544   | 132.686 us |       0.57% | 132.718 us |       0.56% |    0.032 us |   0.02% |   SAME   |
|   I64   |      I32      |      2^20      |   0.544   | 201.310 us |       0.54% | 201.339 us |       0.53% |    0.028 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^24      |   0.544   |   1.439 ms |       0.16% |   1.439 ms |       0.18% |    0.164 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^28      |   0.544   |  21.052 ms |       0.19% |  21.053 ms |       0.19% |    1.300 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^16      |   0.201   | 132.669 us |       0.52% | 132.674 us |       0.48% |    0.005 us |   0.00% |   SAME   |
|   I64   |      I32      |      2^20      |   0.201   | 191.218 us |       0.75% | 191.281 us |       0.79% |    0.063 us |   0.03% |   SAME   |
|   I64   |      I32      |      2^24      |   0.201   |   1.388 ms |       0.19% |   1.388 ms |       0.20% |    0.141 us |   0.01% |   SAME   |
|   I64   |      I32      |      2^28      |   0.201   |  20.278 ms |       0.20% |  20.277 ms |       0.19% |   -0.735 us |  -0.00% |   SAME   |
|   I64   |      I64      |      2^16      |     1     | 132.863 us |       0.71% | 132.874 us |       0.73% |    0.011 us |   0.01% |   SAME   |
|   I64   |      I64      |      2^20      |     1     | 201.017 us |       0.67% | 201.006 us |       0.75% |   -0.011 us |  -0.01% |   SAME   |
|   I64   |      I64      |      2^24      |     1     |   1.447 ms |       0.21% |   1.447 ms |       0.22% |    0.130 us |   0.01% |   SAME   |
|   I64   |      I64      |      2^28      |     1     |  21.101 ms |       0.22% |  21.102 ms |       0.23% |    1.142 us |   0.01% |   SAME   |
|   I64   |      I64      |      2^16      |   0.544   | 132.891 us |       0.70% | 132.932 us |       0.75% |    0.040 us |   0.03% |   SAME   |
|   I64   |      I64      |      2^20      |   0.544   | 196.661 us |       1.07% | 196.835 us |       1.02% |    0.174 us |   0.09% |   SAME   |
|   I64   |      I64      |      2^24      |   0.544   |   1.446 ms |       0.20% |   1.446 ms |       0.20% |   -0.073 us |  -0.01% |   SAME   |
|   I64   |      I64      |      2^28      |   0.544   |  21.056 ms |       0.21% |  21.060 ms |       0.21% |    3.834 us |   0.02% |   SAME   |
|   I64   |      I64      |      2^16      |   0.201   | 131.976 us |       1.23% | 132.045 us |       1.18% |    0.069 us |   0.05% |   SAME   |
|   I64   |      I64      |      2^20      |   0.201   | 192.171 us |       0.44% | 192.209 us |       0.53% |    0.038 us |   0.02% |   SAME   |
|   I64   |      I64      |      2^24      |   0.201   |   1.392 ms |       0.19% |   1.392 ms |       0.19% |   -0.126 us |  -0.01% |   SAME   |
|   I64   |      I64      |      2^28      |   0.201   |  20.282 ms |       0.22% |  20.286 ms |       0.21% |    4.303 us |   0.02% |   SAME   |
|  I128   |      I32      |      2^16      |     1     | 232.949 us |       0.33% | 233.017 us |       0.37% |    0.068 us |   0.03% |   SAME   |
|  I128   |      I32      |      2^20      |     1     | 417.677 us |       0.50% | 417.830 us |       0.50% |    0.153 us |   0.04% |   SAME   |
|  I128   |      I32      |      2^24      |     1     |   3.519 ms |       0.10% |   3.518 ms |       0.10% |   -0.914 us |  -0.03% |   SAME   |
|  I128   |      I32      |      2^28      |     1     |  52.798 ms |       0.06% |  52.798 ms |       0.06% |    0.034 us |   0.00% |   SAME   |
|  I128   |      I32      |      2^16      |   0.544   | 232.315 us |       0.59% | 232.411 us |       0.58% |    0.096 us |   0.04% |   SAME   |
|  I128   |      I32      |      2^20      |   0.544   | 414.293 us |       0.68% | 413.570 us |       0.72% |   -0.724 us |  -0.17% |   SAME   |
|  I128   |      I32      |      2^24      |   0.544   |   3.498 ms |       0.10% |   3.498 ms |       0.09% |    0.207 us |   0.01% |   SAME   |
|  I128   |      I32      |      2^28      |   0.544   |  52.422 ms |       0.07% |  52.420 ms |       0.07% |   -1.940 us |  -0.00% |   SAME   |
|  I128   |      I32      |      2^16      |   0.201   | 226.398 us |       0.71% | 226.915 us |       0.74% |    0.517 us |   0.23% |   SAME   |
|  I128   |      I32      |      2^20      |   0.201   | 404.492 us |       0.49% | 404.626 us |       0.47% |    0.134 us |   0.03% |   SAME   |
|  I128   |      I32      |      2^24      |   0.201   |   3.453 ms |       0.09% |   3.454 ms |       0.10% |    0.584 us |   0.02% |   SAME   |
|  I128   |      I32      |      2^28      |   0.201   |  51.580 ms |       0.07% |  51.584 ms |       0.07% |    3.683 us |   0.01% |   SAME   |
|  I128   |      I64      |      2^16      |     1     | 235.025 us |       0.29% | 235.055 us |       0.29% |    0.030 us |   0.01% |   SAME   |
|  I128   |      I64      |      2^20      |     1     | 419.965 us |       0.44% | 419.949 us |       0.45% |   -0.016 us |  -0.00% |   SAME   |
|  I128   |      I64      |      2^24      |     1     |   3.542 ms |       0.10% |   3.542 ms |       0.10% |    0.082 us |   0.00% |   SAME   |
|  I128   |      I64      |      2^28      |     1     |  53.789 ms |       0.03% |  53.787 ms |       0.03% |   -2.392 us |  -0.00% |   SAME   |
|  I128   |      I64      |      2^16      |   0.544   | 229.653 us |       0.79% | 229.695 us |       0.81% |    0.042 us |   0.02% |   SAME   |
|  I128   |      I64      |      2^20      |   0.544   | 415.631 us |       0.60% | 415.655 us |       0.60% |    0.024 us |   0.01% |   SAME   |
|  I128   |      I64      |      2^24      |   0.544   |   3.524 ms |       0.10% |   3.524 ms |       0.11% |    0.131 us |   0.00% |   SAME   |
|  I128   |      I64      |      2^28      |   0.544   |  53.426 ms |       0.03% |  53.426 ms |       0.03% |   -0.185 us |  -0.00% |   SAME   |
|  I128   |      I64      |      2^16      |   0.201   | 228.221 us |       0.72% | 228.090 us |       0.67% |   -0.131 us |  -0.06% |   SAME   |
|  I128   |      I64      |      2^20      |   0.201   | 407.765 us |       0.59% | 407.945 us |       0.59% |    0.180 us |   0.04% |   SAME   |
|  I128   |      I64      |      2^24      |   0.201   |   3.479 ms |       0.10% |   3.479 ms |       0.11% |   -0.279 us |  -0.01% |   SAME   |
|  I128   |      I64      |      2^28      |   0.201   |  52.644 ms |       0.03% |  52.643 ms |       0.03% |   -0.230 us |  -0.00% |   SAME   |
|   F32   |      I32      |      2^16      |     1     |  75.701 us |       0.90% |  75.631 us |       0.97% |   -0.070 us |  -0.09% |   SAME   |
|   F32   |      I32      |      2^20      |     1     |  96.970 us |       1.30% |  96.882 us |       1.25% |   -0.088 us |  -0.09% |   SAME   |
|   F32   |      I32      |      2^24      |     1     | 453.461 us |       0.35% | 453.339 us |       0.34% |   -0.122 us |  -0.03% |   SAME   |
|   F32   |      I32      |      2^28      |     1     |   6.094 ms |       0.08% |   6.092 ms |       0.05% |   -1.215 us |  -0.02% |   SAME   |
|   F32   |      I32      |      2^16      |   0.544   |  75.754 us |       0.79% |  75.605 us |       0.88% |   -0.149 us |  -0.20% |   SAME   |
|   F32   |      I32      |      2^20      |   0.544   |  98.296 us |       0.77% |  98.173 us |       0.79% |   -0.123 us |  -0.13% |   SAME   |
|   F32   |      I32      |      2^24      |   0.544   | 459.983 us |       0.32% | 459.924 us |       0.38% |   -0.059 us |  -0.01% |   SAME   |
|   F32   |      I32      |      2^28      |   0.544   |   6.175 ms |       0.05% |   6.174 ms |       0.05% |   -0.807 us |  -0.01% |   SAME   |
|   F32   |      I32      |      2^16      |   0.201   |  75.654 us |       0.88% |  75.564 us |       0.85% |   -0.090 us |  -0.12% |   SAME   |
|   F32   |      I32      |      2^20      |   0.201   |  95.550 us |       1.29% |  95.572 us |       1.26% |    0.022 us |   0.02% |   SAME   |
|   F32   |      I32      |      2^24      |   0.201   | 444.787 us |       0.28% | 444.535 us |       0.27% |   -0.252 us |  -0.06% |   SAME   |
|   F32   |      I32      |      2^28      |   0.201   |   5.953 ms |       0.06% |   5.953 ms |       0.06% |   -0.712 us |  -0.01% |   SAME   |
|   F32   |      I64      |      2^16      |     1     |  77.634 us |       0.92% |  77.619 us |       0.93% |   -0.016 us |  -0.02% |   SAME   |
|   F32   |      I64      |      2^20      |     1     |  99.362 us |       1.94% |  99.547 us |       1.79% |    0.185 us |   0.19% |   SAME   |
|   F32   |      I64      |      2^24      |     1     | 411.097 us |       0.33% | 411.121 us |       0.30% |    0.023 us |   0.01% |   SAME   |
|   F32   |      I64      |      2^28      |     1     |   5.304 ms |       0.09% |   5.301 ms |       0.09% |   -3.046 us |  -0.06% |   SAME   |
|   F32   |      I64      |      2^16      |   0.544   |  77.542 us |       0.96% |  77.579 us |       1.01% |    0.037 us |   0.05% |   SAME   |
|   F32   |      I64      |      2^20      |   0.544   | 100.032 us |       1.58% | 100.021 us |       1.59% |   -0.011 us |  -0.01% |   SAME   |
|   F32   |      I64      |      2^24      |   0.544   | 415.910 us |       0.38% | 416.315 us |       0.40% |    0.405 us |   0.10% |   SAME   |
|   F32   |      I64      |      2^28      |   0.544   |   5.387 ms |       0.08% |   5.387 ms |       0.08% |   -0.034 us |  -0.00% |   SAME   |
|   F32   |      I64      |      2^16      |   0.201   |  77.639 us |       0.88% |  77.592 us |       0.91% |   -0.047 us |  -0.06% |   SAME   |
|   F32   |      I64      |      2^20      |   0.201   |  97.700 us |       1.44% |  97.872 us |       1.46% |    0.172 us |   0.18% |   SAME   |
|   F32   |      I64      |      2^24      |   0.201   | 403.122 us |       0.42% | 403.242 us |       0.42% |    0.120 us |   0.03% |   SAME   |
|   F32   |      I64      |      2^28      |   0.201   |   5.156 ms |       0.07% |   5.156 ms |       0.08% |   -0.096 us |  -0.00% |   SAME   |
|   F64   |      I32      |      2^16      |     1     | 132.969 us |       0.76% | 132.878 us |       0.69% |   -0.091 us |  -0.07% |   SAME   |
|   F64   |      I32      |      2^20      |     1     | 187.147 us |       0.84% | 187.345 us |       0.78% |    0.198 us |   0.11% |   SAME   |
|   F64   |      I32      |      2^24      |     1     |   1.080 ms |       0.24% |   1.080 ms |       0.24% |   -0.120 us |  -0.01% |   SAME   |
|   F64   |      I32      |      2^28      |     1     |  15.304 ms |       0.04% |  15.304 ms |       0.04% |   -0.170 us |  -0.00% |   SAME   |
|   F64   |      I32      |      2^16      |   0.544   | 133.276 us |       0.89% | 133.243 us |       0.90% |   -0.033 us |  -0.02% |   SAME   |
|   F64   |      I32      |      2^20      |   0.544   | 188.065 us |       0.52% | 188.050 us |       0.49% |   -0.016 us |  -0.01% |   SAME   |
|   F64   |      I32      |      2^24      |   0.544   |   1.098 ms |       0.22% |   1.098 ms |       0.21% |   -0.038 us |  -0.00% |   SAME   |
|   F64   |      I32      |      2^28      |   0.544   |  15.546 ms |       0.03% |  15.546 ms |       0.03% |   -0.106 us |  -0.00% |   SAME   |
|   F64   |      I32      |      2^16      |   0.201   | 133.841 us |       1.06% | 133.845 us |       1.05% |    0.004 us |   0.00% |   SAME   |
|   F64   |      I32      |      2^20      |   0.201   | 185.998 us |       0.49% | 185.935 us |       0.48% |   -0.064 us |  -0.03% |   SAME   |
|   F64   |      I32      |      2^24      |   0.201   |   1.065 ms |       0.26% |   1.066 ms |       0.24% |    0.266 us |   0.02% |   SAME   |
|   F64   |      I32      |      2^28      |   0.201   |  14.988 ms |       0.05% |  14.987 ms |       0.05% |   -0.355 us |  -0.00% |   SAME   |
|   F64   |      I64      |      2^16      |     1     | 132.892 us |       0.70% | 132.869 us |       0.70% |   -0.023 us |  -0.02% |   SAME   |
|   F64   |      I64      |      2^20      |     1     | 188.002 us |       0.84% | 187.904 us |       0.82% |   -0.099 us |  -0.05% |   SAME   |
|   F64   |      I64      |      2^24      |     1     |   1.068 ms |       0.18% |   1.067 ms |       0.18% |   -0.339 us |  -0.03% |   SAME   |
|   F64   |      I64      |      2^28      |     1     |  15.256 ms |       0.04% |  15.255 ms |       0.04% |   -0.374 us |  -0.00% |   SAME   |
|   F64   |      I64      |      2^16      |   0.544   | 132.988 us |       0.72% | 133.034 us |       0.75% |    0.045 us |   0.03% |   SAME   |
|   F64   |      I64      |      2^20      |   0.544   | 188.109 us |       0.52% | 188.125 us |       0.52% |    0.016 us |   0.01% |   SAME   |
|   F64   |      I64      |      2^24      |   0.544   |   1.086 ms |       0.16% |   1.086 ms |       0.17% |   -0.098 us |  -0.01% |   SAME   |
|   F64   |      I64      |      2^28      |   0.544   |  15.489 ms |       0.04% |  15.489 ms |       0.04% |   -0.872 us |  -0.01% |   SAME   |
|   F64   |      I64      |      2^16      |   0.201   | 132.560 us |       0.57% | 132.919 us |       0.69% |    0.360 us |   0.27% |   SAME   |
|   F64   |      I64      |      2^20      |   0.201   | 185.739 us |       0.53% | 186.010 us |       0.57% |    0.270 us |   0.15% |   SAME   |
|   F64   |      I64      |      2^24      |   0.201   |   1.053 ms |       0.22% |   1.053 ms |       0.21% |    0.546 us |   0.05% |   SAME   |
|   F64   |      I64      |      2^28      |   0.201   |  14.912 ms |       0.11% |  14.912 ms |       0.10% |   -0.210 us |  -0.00% |   SAME   |

Copy link
Contributor

🟩 CI finished in 1h 56m: Pass: 100%/89 | Total: 2d 14h | Avg: 41m 58s | Max: 1h 16m | Hits: 262%/10936
  • 🟩 cub: Pass: 100%/44 | Total: 1d 14h | Avg: 52m 23s | Max: 1h 16m | Hits: 325%/3552

    🟩 cpu
      🟩 amd64              Pass: 100%/42  | Total:  1d 12h | Avg: 52m 00s | Max:  1h 16m | Hits: 325%/3552  
      🟩 arm64              Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 02m
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  4h 58m | Avg: 59m 47s | Max:  1h 06m | Hits: 355%/888   
      🟩 12.5               Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 13m
      🟩 12.6               Pass: 100%/37  | Total:  1d 07h | Avg: 50m 23s | Max:  1h 16m | Hits: 316%/2664  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  2h 05m | Avg:  1h 02m | Max:  1h 04m
      🟩 nvcc12.0           Pass: 100%/5   | Total:  4h 58m | Avg: 59m 47s | Max:  1h 06m | Hits: 355%/888   
      🟩 nvcc12.5           Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 13m
      🟩 nvcc12.6           Pass: 100%/35  | Total:  1d 04h | Avg: 49m 40s | Max:  1h 16m | Hits: 316%/2664  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  2h 05m | Avg:  1h 02m | Max:  1h 04m
      🟩 nvcc               Pass: 100%/42  | Total:  1d 12h | Avg: 51m 54s | Max:  1h 16m | Hits: 325%/3552  
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  3h 48m | Avg: 57m 03s | Max:  1h 00m
      🟩 Clang15            Pass: 100%/2   | Total:  1h 49m | Avg: 54m 38s | Max: 56m 30s
      🟩 Clang16            Pass: 100%/2   | Total:  1h 51m | Avg: 55m 30s | Max: 56m 26s
      🟩 Clang17            Pass: 100%/2   | Total:  1h 56m | Avg: 58m 10s | Max: 58m 54s
      🟩 Clang18            Pass: 100%/7   | Total:  5h 38m | Avg: 48m 25s | Max:  1h 04m
      🟩 GCC7               Pass: 100%/2   | Total:  1h 55m | Avg: 57m 33s | Max:  1h 00m
      🟩 GCC8               Pass: 100%/1   | Total: 54m 16s | Avg: 54m 16s | Max: 54m 16s
      🟩 GCC9               Pass: 100%/2   | Total:  1h 53m | Avg: 56m 56s | Max: 59m 29s
      🟩 GCC10              Pass: 100%/2   | Total:  1h 58m | Avg: 59m 05s | Max:  1h 01m
      🟩 GCC11              Pass: 100%/2   | Total:  1h 52m | Avg: 56m 10s | Max: 57m 11s
      🟩 GCC12              Pass: 100%/4   | Total:  2h 56m | Avg: 44m 00s | Max:  1h 03m
      🟩 GCC13              Pass: 100%/8   | Total:  4h 48m | Avg: 36m 00s | Max:  1h 02m
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 14m | Avg:  1h 07m | Max:  1h 08m | Hits: 299%/1776  
      🟩 MSVC14.39          Pass: 100%/2   | Total:  2h 27m | Avg:  1h 13m | Max:  1h 16m | Hits: 352%/1776  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 13m
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total: 15h 03m | Avg: 53m 10s | Max:  1h 04m
      🟩 GCC                Pass: 100%/21  | Total: 16h 17m | Avg: 46m 34s | Max:  1h 03m
      🟩 MSVC               Pass: 100%/4   | Total:  4h 41m | Avg:  1h 10m | Max:  1h 16m | Hits: 325%/3552  
      🟩 NVHPC              Pass: 100%/2   | Total:  2h 22m | Avg:  1h 11m | Max:  1h 13m
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 56m 09s | Avg: 28m 04s | Max: 29m 07s
      🟩 rtxa6000           Pass: 100%/8   | Total:  4h 06m | Avg: 30m 47s | Max: 57m 15s
      🟩 v100               Pass: 100%/34  | Total:  1d 09h | Avg: 58m 55s | Max:  1h 16m | Hits: 325%/3552  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total:  1d 11h | Avg: 57m 55s | Max:  1h 16m | Hits: 325%/3552  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 20m 57s | Avg: 20m 57s | Max: 20m 57s
      🟩 GraphCapture       Pass: 100%/1   | Total: 17m 30s | Avg: 17m 30s | Max: 17m 30s
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 22m | Avg: 27m 36s | Max: 29m 07s
      🟩 TestGPU            Pass: 100%/2   | Total: 41m 22s | Avg: 20m 41s | Max: 22m 57s
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 56m 09s | Avg: 28m 04s | Max: 29m 07s
      🟩 90a                Pass: 100%/1   | Total: 23m 37s | Avg: 23m 37s | Max: 23m 37s
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 19h 50m | Avg: 59m 31s | Max:  1h 10m | Hits: 316%/2664  
      🟩 20                 Pass: 100%/24  | Total: 18h 35m | Avg: 46m 28s | Max:  1h 16m | Hits: 354%/888   
    
  • 🟩 thrust: Pass: 100%/42 | Total: 23h 06m | Avg: 33m 00s | Max: 1h 04m | Hits: 231%/7384

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 37m 14s | Avg: 18m 37s | Max: 25m 54s
    🟩 cpu
      🟩 amd64              Pass: 100%/40  | Total: 22h 07m | Avg: 33m 11s | Max:  1h 04m | Hits: 231%/7384  
      🟩 arm64              Pass: 100%/2   | Total: 58m 18s | Avg: 29m 09s | Max: 30m 02s
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  3h 01m | Avg: 36m 18s | Max: 56m 38s | Hits: 237%/1846  
      🟩 12.5               Pass: 100%/2   | Total:  1h 47m | Avg: 53m 46s | Max: 54m 31s
      🟩 12.6               Pass: 100%/35  | Total: 18h 17m | Avg: 31m 20s | Max:  1h 04m | Hits: 229%/5538  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 56m 22s | Avg: 28m 11s | Max: 28m 47s
      🟩 nvcc12.0           Pass: 100%/5   | Total:  3h 01m | Avg: 36m 18s | Max: 56m 38s | Hits: 237%/1846  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 47m | Avg: 53m 46s | Max: 54m 31s
      🟩 nvcc12.6           Pass: 100%/33  | Total: 17h 20m | Avg: 31m 32s | Max:  1h 04m | Hits: 229%/5538  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 56m 22s | Avg: 28m 11s | Max: 28m 47s
      🟩 nvcc               Pass: 100%/40  | Total: 22h 09m | Avg: 33m 14s | Max:  1h 04m | Hits: 231%/7384  
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  2h 08m | Avg: 32m 11s | Max: 39m 11s
      🟩 Clang15            Pass: 100%/2   | Total:  1h 04m | Avg: 32m 00s | Max: 32m 24s
      🟩 Clang16            Pass: 100%/2   | Total:  1h 03m | Avg: 31m 35s | Max: 32m 52s
      🟩 Clang17            Pass: 100%/2   | Total:  1h 04m | Avg: 32m 28s | Max: 34m 18s
      🟩 Clang18            Pass: 100%/7   | Total:  2h 48m | Avg: 24m 00s | Max: 33m 01s
      🟩 GCC7               Pass: 100%/2   | Total:  1h 03m | Avg: 31m 41s | Max: 33m 01s
      🟩 GCC8               Pass: 100%/1   | Total: 31m 37s | Avg: 31m 37s | Max: 31m 37s
      🟩 GCC9               Pass: 100%/2   | Total:  1h 08m | Avg: 34m 12s | Max: 34m 27s
      🟩 GCC10              Pass: 100%/2   | Total:  1h 08m | Avg: 34m 06s | Max: 34m 16s
      🟩 GCC11              Pass: 100%/2   | Total:  1h 03m | Avg: 31m 59s | Max: 33m 18s
      🟩 GCC12              Pass: 100%/2   | Total:  1h 09m | Avg: 34m 58s | Max: 36m 38s
      🟩 GCC13              Pass: 100%/8   | Total:  2h 56m | Avg: 22m 01s | Max: 36m 06s
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 00m | Avg:  1h 00m | Max:  1h 03m | Hits: 237%/3692  
      🟩 MSVC14.39          Pass: 100%/2   | Total:  2h 07m | Avg:  1h 03m | Max:  1h 04m | Hits: 225%/3692  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 47m | Avg: 53m 46s | Max: 54m 31s
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  8h 08m | Avg: 28m 45s | Max: 39m 11s
      🟩 GCC                Pass: 100%/19  | Total:  9h 01m | Avg: 28m 30s | Max: 36m 38s
      🟩 MSVC               Pass: 100%/4   | Total:  4h 07m | Avg:  1h 01m | Max:  1h 04m | Hits: 231%/7384  
      🟩 NVHPC              Pass: 100%/2   | Total:  1h 47m | Avg: 53m 46s | Max: 54m 31s
    🟩 gpu
      🟩 rtx4090            Pass: 100%/8   | Total:  2h 20m | Avg: 17m 36s | Max: 33m 47s
      🟩 v100               Pass: 100%/34  | Total: 20h 45m | Avg: 36m 37s | Max:  1h 04m | Hits: 231%/7384  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total: 22h 17m | Avg: 36m 08s | Max:  1h 04m | Hits: 231%/7384  
      🟩 TestCPU            Pass: 100%/2   | Total: 16m 02s | Avg:  8m 01s | Max:  8m 06s
      🟩 TestGPU            Pass: 100%/3   | Total: 33m 00s | Avg: 11m 00s | Max: 11m 32s
    🟩 sm
      🟩 90a                Pass: 100%/1   | Total: 19m 32s | Avg: 19m 32s | Max: 19m 32s
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 12h 40m | Avg: 38m 01s | Max:  1h 03m | Hits: 238%/5538  
      🟩 20                 Pass: 100%/20  | Total:  9h 48m | Avg: 29m 25s | Max:  1h 04m | Hits: 210%/1846  
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 14m 36s | Avg: 7m 18s | Max: 12m 18s

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 ctk
      🟩 12.6               Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 cudacxx
      🟩 nvcc12.6           Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total: 14m 36s | Avg:  7m 18s | Max: 12m 18s
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  2m 18s | Avg:  2m 18s | Max:  2m 18s
      🟩 Test               Pass: 100%/1   | Total: 12m 18s | Avg: 12m 18s | Max: 12m 18s
    
  • 🟩 python: Pass: 100%/1 | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 ctk
      🟩 12.6               Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 cudacxx
      🟩 nvcc12.6           Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 29m 59s | Avg: 29m 59s | Max: 29m 59s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
python
CCCL C Parallel Library
Catch2Helper

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- python
+/- CCCL C Parallel Library
+/- Catch2Helper

🏃‍ Runner counts (total jobs: 89)

# Runner
65 linux-amd64-cpu16
8 windows-amd64-cpu16
6 linux-amd64-gpu-rtxa6000-latest-1
4 linux-arm64-cpu16
3 linux-amd64-gpu-rtx4090-latest-1
2 linux-amd64-gpu-rtx2080-latest-1
1 linux-amd64-gpu-h100-latest-1

@miscco miscco enabled auto-merge (squash) January 30, 2025 18:16
@bernhardmgruber bernhardmgruber marked this pull request as draft January 31, 2025 11:23
@NVIDIA NVIDIA deleted a comment from copy-pr-bot bot Jan 31, 2025
@bernhardmgruber bernhardmgruber changed the title Add b200 tunings for radix_sort.keys,pairs Add b200 tunings for radix_sort.keys Jan 31, 2025
@bernhardmgruber bernhardmgruber marked this pull request as ready for review January 31, 2025 11:31
@bernhardmgruber bernhardmgruber enabled auto-merge (squash) January 31, 2025 11:31
Copy link
Contributor

🟩 CI finished in 1h 29m: Pass: 100%/89 | Total: 2d 01h | Avg: 33m 31s | Max: 1h 09m | Hits: 369%/10896
  • 🟩 cub: Pass: 100%/44 | Total: 1d 13h | Avg: 51m 48s | Max: 1h 09m | Hits: 438%/3512

    🟩 cpu
      🟩 amd64              Pass: 100%/42  | Total:  1d 11h | Avg: 51m 24s | Max:  1h 09m | Hits: 438%/3512  
      🟩 arm64              Pass: 100%/2   | Total:  2h 00m | Avg:  1h 00m | Max:  1h 01m
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  4h 55m | Avg: 59m 04s | Max:  1h 01m | Hits: 436%/878   
      🟩 12.5               Pass: 100%/2   | Total:  2h 15m | Avg:  1h 07m | Max:  1h 08m
      🟩 12.6               Pass: 100%/37  | Total:  1d 06h | Avg: 49m 58s | Max:  1h 09m | Hits: 438%/2634  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total:  1h 51m | Avg: 55m 32s | Max: 55m 52s
      🟩 nvcc12.0           Pass: 100%/5   | Total:  4h 55m | Avg: 59m 04s | Max:  1h 01m | Hits: 436%/878   
      🟩 nvcc12.5           Pass: 100%/2   | Total:  2h 15m | Avg:  1h 07m | Max:  1h 08m
      🟩 nvcc12.6           Pass: 100%/35  | Total:  1d 04h | Avg: 49m 39s | Max:  1h 09m | Hits: 438%/2634  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total:  1h 51m | Avg: 55m 32s | Max: 55m 52s
      🟩 nvcc               Pass: 100%/42  | Total:  1d 12h | Avg: 51m 38s | Max:  1h 09m | Hits: 438%/3512  
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total:  3h 49m | Avg: 57m 18s | Max: 59m 42s
      🟩 Clang15            Pass: 100%/2   | Total:  1h 51m | Avg: 55m 35s | Max: 56m 53s
      🟩 Clang16            Pass: 100%/2   | Total:  2h 01m | Avg:  1h 00m | Max:  1h 01m
      🟩 Clang17            Pass: 100%/2   | Total:  1h 51m | Avg: 55m 38s | Max: 55m 57s
      🟩 Clang18            Pass: 100%/7   | Total:  5h 35m | Avg: 47m 58s | Max:  1h 01m
      🟩 GCC7               Pass: 100%/2   | Total:  2h 02m | Avg:  1h 01m | Max:  1h 03m
      🟩 GCC8               Pass: 100%/1   | Total: 57m 03s | Avg: 57m 03s | Max: 57m 03s
      🟩 GCC9               Pass: 100%/2   | Total:  1h 56m | Avg: 58m 14s | Max:  1h 00m
      🟩 GCC10              Pass: 100%/2   | Total:  1h 52m | Avg: 56m 18s | Max: 57m 09s
      🟩 GCC11              Pass: 100%/2   | Total:  1h 51m | Avg: 55m 51s | Max: 57m 19s
      🟩 GCC12              Pass: 100%/4   | Total:  2h 46m | Avg: 41m 43s | Max:  1h 00m
      🟩 GCC13              Pass: 100%/8   | Total:  4h 47m | Avg: 35m 56s | Max:  1h 01m
      🟩 MSVC14.29          Pass: 100%/2   | Total:  2h 06m | Avg:  1h 03m | Max:  1h 04m | Hits: 437%/1756  
      🟩 MSVC14.39          Pass: 100%/2   | Total:  2h 14m | Avg:  1h 07m | Max:  1h 09m | Hits: 438%/1756  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  2h 15m | Avg:  1h 07m | Max:  1h 08m
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total: 15h 09m | Avg: 53m 29s | Max:  1h 01m
      🟩 GCC                Pass: 100%/21  | Total: 16h 14m | Avg: 46m 23s | Max:  1h 03m
      🟩 MSVC               Pass: 100%/4   | Total:  4h 21m | Avg:  1h 05m | Max:  1h 09m | Hits: 438%/3512  
      🟩 NVHPC              Pass: 100%/2   | Total:  2h 15m | Avg:  1h 07m | Max:  1h 08m
    🟩 gpu
      🟩 h100               Pass: 100%/2   | Total: 50m 55s | Avg: 25m 27s | Max: 26m 18s
      🟩 rtxa6000           Pass: 100%/8   | Total:  4h 08m | Avg: 31m 05s | Max:  1h 01m
      🟩 v100               Pass: 100%/34  | Total:  1d 09h | Avg: 58m 14s | Max:  1h 09m | Hits: 438%/3512  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total:  1d 11h | Avg: 57m 27s | Max:  1h 09m | Hits: 438%/3512  
      🟩 DeviceLaunch       Pass: 100%/1   | Total: 19m 29s | Avg: 19m 29s | Max: 19m 29s
      🟩 GraphCapture       Pass: 100%/1   | Total: 15m 32s | Avg: 15m 32s | Max: 15m 32s
      🟩 HostLaunch         Pass: 100%/3   | Total:  1h 15m | Avg: 25m 16s | Max: 26m 18s
      🟩 TestGPU            Pass: 100%/2   | Total: 43m 00s | Avg: 21m 30s | Max: 21m 43s
    🟩 sm
      🟩 90                 Pass: 100%/2   | Total: 50m 55s | Avg: 25m 27s | Max: 26m 18s
      🟩 90a                Pass: 100%/1   | Total: 27m 07s | Avg: 27m 07s | Max: 27m 07s
    🟩 std
      🟩 17                 Pass: 100%/20  | Total: 19h 38m | Avg: 58m 55s | Max:  1h 09m | Hits: 438%/2634  
      🟩 20                 Pass: 100%/24  | Total: 18h 21m | Avg: 45m 53s | Max:  1h 08m | Hits: 438%/878   
    
  • 🟩 thrust: Pass: 100%/42 | Total: 11h 03m | Avg: 15m 48s | Max: 40m 30s | Hits: 337%/7384

    🟩 cmake_options
      🟩 -DTHRUST_DISPATCH_TYPE=Force32bit Pass: 100%/2   | Total: 23m 20s | Avg: 11m 40s | Max: 11m 59s
    🟩 cpu
      🟩 amd64              Pass: 100%/40  | Total: 10h 39m | Avg: 15m 59s | Max: 40m 30s | Hits: 337%/7384  
      🟩 arm64              Pass: 100%/2   | Total: 24m 11s | Avg: 12m 05s | Max: 12m 51s
    🟩 ctk
      🟩 12.0               Pass: 100%/5   | Total:  1h 23m | Avg: 16m 39s | Max: 30m 10s | Hits: 339%/1846  
      🟩 12.5               Pass: 100%/2   | Total:  1h 04m | Avg: 32m 29s | Max: 33m 17s
      🟩 12.6               Pass: 100%/35  | Total:  8h 35m | Avg: 14m 43s | Max: 40m 30s | Hits: 336%/5538  
    🟩 cudacxx
      🟩 ClangCUDA18        Pass: 100%/2   | Total: 23m 01s | Avg: 11m 30s | Max: 11m 59s
      🟩 nvcc12.0           Pass: 100%/5   | Total:  1h 23m | Avg: 16m 39s | Max: 30m 10s | Hits: 339%/1846  
      🟩 nvcc12.5           Pass: 100%/2   | Total:  1h 04m | Avg: 32m 29s | Max: 33m 17s
      🟩 nvcc12.6           Pass: 100%/33  | Total:  8h 12m | Avg: 14m 55s | Max: 40m 30s | Hits: 336%/5538  
    🟩 cudacxx_family
      🟩 ClangCUDA          Pass: 100%/2   | Total: 23m 01s | Avg: 11m 30s | Max: 11m 59s
      🟩 nvcc               Pass: 100%/40  | Total: 10h 40m | Avg: 16m 01s | Max: 40m 30s | Hits: 337%/7384  
    🟩 cxx
      🟩 Clang14            Pass: 100%/4   | Total: 51m 21s | Avg: 12m 50s | Max: 13m 20s
      🟩 Clang15            Pass: 100%/2   | Total: 27m 00s | Avg: 13m 30s | Max: 13m 44s
      🟩 Clang16            Pass: 100%/2   | Total: 27m 23s | Avg: 13m 41s | Max: 14m 15s
      🟩 Clang17            Pass: 100%/2   | Total: 25m 40s | Avg: 12m 50s | Max: 13m 12s
      🟩 Clang18            Pass: 100%/7   | Total:  1h 20m | Avg: 11m 32s | Max: 14m 22s
      🟩 GCC7               Pass: 100%/2   | Total: 27m 08s | Avg: 13m 34s | Max: 14m 08s
      🟩 GCC8               Pass: 100%/1   | Total: 13m 18s | Avg: 13m 18s | Max: 13m 18s
      🟩 GCC9               Pass: 100%/2   | Total: 28m 04s | Avg: 14m 02s | Max: 14m 17s
      🟩 GCC10              Pass: 100%/2   | Total: 27m 45s | Avg: 13m 52s | Max: 14m 27s
      🟩 GCC11              Pass: 100%/2   | Total: 27m 07s | Avg: 13m 33s | Max: 13m 35s
      🟩 GCC12              Pass: 100%/2   | Total: 27m 41s | Avg: 13m 50s | Max: 14m 11s
      🟩 GCC13              Pass: 100%/8   | Total:  1h 32m | Avg: 11m 35s | Max: 15m 16s
      🟩 MSVC14.29          Pass: 100%/2   | Total:  1h 06m | Avg: 33m 13s | Max: 36m 17s | Hits: 339%/3692  
      🟩 MSVC14.39          Pass: 100%/2   | Total:  1h 16m | Avg: 38m 13s | Max: 40m 30s | Hits: 334%/3692  
      🟩 NVHPC24.7          Pass: 100%/2   | Total:  1h 04m | Avg: 32m 29s | Max: 33m 17s
    🟩 cxx_family
      🟩 Clang              Pass: 100%/17  | Total:  3h 32m | Avg: 12m 28s | Max: 14m 22s
      🟩 GCC                Pass: 100%/19  | Total:  4h 03m | Avg: 12m 50s | Max: 15m 16s
      🟩 MSVC               Pass: 100%/4   | Total:  2h 22m | Avg: 35m 43s | Max: 40m 30s | Hits: 337%/7384  
      🟩 NVHPC              Pass: 100%/2   | Total:  1h 04m | Avg: 32m 29s | Max: 33m 17s
    🟩 gpu
      🟩 rtx4090            Pass: 100%/8   | Total:  1h 30m | Avg: 11m 20s | Max: 15m 16s
      🟩 v100               Pass: 100%/34  | Total:  9h 33m | Avg: 16m 51s | Max: 40m 30s | Hits: 337%/7384  
    🟩 jobs
      🟩 Build              Pass: 100%/37  | Total: 10h 14m | Avg: 16m 37s | Max: 40m 30s | Hits: 337%/7384  
      🟩 TestCPU            Pass: 100%/2   | Total: 15m 41s | Avg:  7m 50s | Max:  7m 58s
      🟩 TestGPU            Pass: 100%/3   | Total: 33m 23s | Avg: 11m 07s | Max: 11m 31s
    🟩 sm
      🟩 90a                Pass: 100%/1   | Total:  7m 46s | Avg:  7m 46s | Max:  7m 46s
    🟩 std
      🟩 17                 Pass: 100%/20  | Total:  5h 47m | Avg: 17m 23s | Max: 36m 17s | Hits: 339%/5538  
      🟩 20                 Pass: 100%/20  | Total:  4h 52m | Avg: 14m 38s | Max: 40m 30s | Hits: 328%/1846  
    
  • 🟩 cccl_c_parallel: Pass: 100%/2 | Total: 7m 56s | Avg: 3m 58s | Max: 6m 00s

    🟩 cpu
      🟩 amd64              Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 ctk
      🟩 12.6               Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 cudacxx
      🟩 nvcc12.6           Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 cxx
      🟩 GCC13              Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/2   | Total:  7m 56s | Avg:  3m 58s | Max:  6m 00s
    🟩 jobs
      🟩 Build              Pass: 100%/1   | Total:  1m 56s | Avg:  1m 56s | Max:  1m 56s
      🟩 Test               Pass: 100%/1   | Total:  6m 00s | Avg:  6m 00s | Max:  6m 00s
    
  • 🟩 python: Pass: 100%/1 | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s

    🟩 cpu
      🟩 amd64              Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 ctk
      🟩 12.6               Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 cudacxx
      🟩 nvcc12.6           Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 cudacxx_family
      🟩 nvcc               Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 cxx
      🟩 GCC13              Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 cxx_family
      🟩 GCC                Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 gpu
      🟩 rtx2080            Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    🟩 jobs
      🟩 Test               Pass: 100%/1   | Total: 31m 29s | Avg: 31m 29s | Max: 31m 29s
    

👃 Inspect Changes

Modifications in project?

Project
CCCL Infrastructure
libcu++
+/- CUB
Thrust
CUDA Experimental
python
CCCL C Parallel Library
Catch2Helper

Modifications in project or dependencies?

Project
CCCL Infrastructure
libcu++
+/- CUB
+/- Thrust
CUDA Experimental
+/- python
+/- CCCL C Parallel Library
+/- Catch2Helper

🏃‍ Runner counts (total jobs: 89)

# Runner
65 linux-amd64-cpu16
8 windows-amd64-cpu16
6 linux-amd64-gpu-rtxa6000-latest-1
4 linux-arm64-cpu16
3 linux-amd64-gpu-rtx4090-latest-1
2 linux-amd64-gpu-rtx2080-latest-1
1 linux-amd64-gpu-h100-latest-1

@bernhardmgruber bernhardmgruber merged commit 2255303 into NVIDIA:main Jan 31, 2025
105 of 109 checks passed
Copy link
Contributor

Git push to origin failed for branch/2.8.x with exitcode 128

@bernhardmgruber bernhardmgruber deleted the tune_radix_sort branch January 31, 2025 14:55
bernhardmgruber added a commit to bernhardmgruber/cccl that referenced this pull request Feb 3, 2025
bernhardmgruber added a commit to bernhardmgruber/cccl that referenced this pull request Feb 4, 2025
bernhardmgruber added a commit to bernhardmgruber/cccl that referenced this pull request Feb 4, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

3 participants