SPEC2017 INTrate: LTO -Ofast - Different x86_64 levels
-flto -Ofast
AMD EPYC 7543P (zen3 based Milan)
Run-times
Benchmark
x86-64
x86-64-v2
x86-64-v3
x86-64-v2
x86-64-v3
500.perlbench_r
100.00%
101.66%
102.48%
100.00%
100.81%
502.gcc_r
100.00%
100.00%
100.00%
100.00%
100.00%
505.mcf_r
100.00%
101.18%
100.71%
100.00%
99.53%
520.omnetpp_r
100.00%
98.63%
99.77%
100.00%
101.15%
523.xalancbmk_r
100.00%
101.56%
100.67%
100.00%
99.12%
525.x264_r
100.00%
96.36%
107.00%
100.00%
111.05%
531.deepsjeng_r
100.00%
95.69%
93.02%
100.00%
97.21%
541.leela_r
100.00%
101.32%
100.00%
100.00%
98.70%
548.exchange2_r
100.00%
100.75%
100.00%
100.00%
99.26%
557.xz_r
100.00%
100.00%
100.41%
100.00%
100.41%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 101.66% | 102.48% | 100.00% | 100.81% |
| 502.gcc_r | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% |
| 505.mcf_r | 100.00% | 101.18% | 100.71% | 100.00% | 99.53% |
| 520.omnetpp_r | 100.00% | 98.63% | 99.77% | 100.00% | 101.15% |
| 523.xalancbmk_r | 100.00% | 101.56% | 100.67% | 100.00% | 99.12% |
| 525.x264_r | 100.00% | 96.36% | 107.00% | 100.00% | 111.05% |
| 531.deepsjeng_r | 100.00% | 95.69% | 93.02% | 100.00% | 97.21% |
| 541.leela_r | 100.00% | 101.32% | 100.00% | 100.00% | 98.70% |
| 548.exchange2_r | 100.00% | 100.75% | 100.00% | 100.00% | 99.26% |
| 557.xz_r | 100.00% | 100.00% | 100.41% | 100.00% | 100.41% |
Naturally, the smaller the run-times, the better. On the other hand, rates and especially their geometric means are better when they are greater.
See also continuous gcc tuning benchmarking at https://lnt.opensuse.org/db_default/v4/SPEC/spec_report/tuning.
Non-debug executable sizes
Click to display/hide
Benchmark
x86-64
x86-64-v2
x86-64-v3
x86-64-v2
x86-64-v3
500.perlbench_r
100.00%
100.00%
100.83%
100.00%
100.83%
502.gcc_r
100.00%
100.03%
100.70%
100.00%
100.67%
505.mcf_r
100.00%
100.00%
109.38%
100.00%
109.38%
520.omnetpp_r
100.00%
99.94%
101.11%
100.00%
101.17%
523.xalancbmk_r
100.00%
100.01%
101.29%
100.00%
101.28%
525.x264_r
100.00%
97.18%
97.42%
100.00%
100.25%
531.deepsjeng_r
100.00%
99.99%
100.01%
100.00%
100.02%
541.leela_r
100.00%
100.42%
101.40%
100.00%
100.98%
548.exchange2_r
100.00%
99.71%
122.29%
100.00%
122.65%
557.xz_r
100.00%
99.89%
101.89%
100.00%
102.01%
Smaller binary sizes are always better.
Click to display/hide
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 100.00% | 100.83% | 100.00% | 100.83% |
| 502.gcc_r | 100.00% | 100.03% | 100.70% | 100.00% | 100.67% |
| 505.mcf_r | 100.00% | 100.00% | 109.38% | 100.00% | 109.38% |
| 520.omnetpp_r | 100.00% | 99.94% | 101.11% | 100.00% | 101.17% |
| 523.xalancbmk_r | 100.00% | 100.01% | 101.29% | 100.00% | 101.28% |
| 525.x264_r | 100.00% | 97.18% | 97.42% | 100.00% | 100.25% |
| 531.deepsjeng_r | 100.00% | 99.99% | 100.01% | 100.00% | 100.02% |
| 541.leela_r | 100.00% | 100.42% | 101.40% | 100.00% | 100.98% |
| 548.exchange2_r | 100.00% | 99.71% | 122.29% | 100.00% | 122.65% |
| 557.xz_r | 100.00% | 99.89% | 101.89% | 100.00% | 102.01% |
Intel Cascade Lake Xeon
Run-times
Benchmark
x86-64
x86-64-v2
x86-64-v3
x86-64-v2
x86-64-v3
500.perlbench_r
100.00%
100.62%
102.49%
100.00%
101.86%
502.gcc_r
100.00%
99.58%
99.58%
100.00%
100.00%
505.mcf_r
100.00%
102.80%
102.56%
100.00%
99.77%
520.omnetpp_r
100.00%
99.30%
99.30%
100.00%
100.00%
523.xalancbmk_r
100.00%
100.67%
101.11%
100.00%
100.44%
525.x264_r
100.00%
96.11%
98.45%
100.00%
102.43%
531.deepsjeng_r
100.00%
95.78%
92.62%
100.00%
96.70%
541.leela_r
100.00%
100.67%
101.12%
100.00%
100.44%
548.exchange2_r
100.00%
100.00%
99.34%
100.00%
99.34%
557.xz_r
100.00%
100.64%
100.64%
100.00%
100.00%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 100.62% | 102.49% | 100.00% | 101.86% |
| 502.gcc_r | 100.00% | 99.58% | 99.58% | 100.00% | 100.00% |
| 505.mcf_r | 100.00% | 102.80% | 102.56% | 100.00% | 99.77% |
| 520.omnetpp_r | 100.00% | 99.30% | 99.30% | 100.00% | 100.00% |
| 523.xalancbmk_r | 100.00% | 100.67% | 101.11% | 100.00% | 100.44% |
| 525.x264_r | 100.00% | 96.11% | 98.45% | 100.00% | 102.43% |
| 531.deepsjeng_r | 100.00% | 95.78% | 92.62% | 100.00% | 96.70% |
| 541.leela_r | 100.00% | 100.67% | 101.12% | 100.00% | 100.44% |
| 548.exchange2_r | 100.00% | 100.00% | 99.34% | 100.00% | 99.34% |
| 557.xz_r | 100.00% | 100.64% | 100.64% | 100.00% | 100.00% |
Naturally, the smaller the run-times, the better. On the other hand, rates and especially their geometric means are better when they are greater.
See also continuous gcc tuning benchmarking at https://lnt.opensuse.org/db_default/v4/SPEC/spec_report/tuning.
Non-debug executable sizes
Click to display/hide
Benchmark
x86-64
x86-64-v2
x86-64-v3
x86-64-v2
x86-64-v3
500.perlbench_r
100.00%
100.00%
100.83%
100.00%
100.83%
502.gcc_r
100.00%
100.03%
100.70%
100.00%
100.67%
505.mcf_r
100.00%
100.00%
109.38%
100.00%
109.38%
520.omnetpp_r
100.00%
99.94%
101.11%
100.00%
101.17%
523.xalancbmk_r
100.00%
100.01%
101.29%
100.00%
101.28%
525.x264_r
100.00%
97.18%
97.42%
100.00%
100.25%
531.deepsjeng_r
100.00%
99.99%
100.01%
100.00%
100.02%
541.leela_r
100.00%
100.42%
101.40%
100.00%
100.98%
548.exchange2_r
100.00%
99.71%
122.29%
100.00%
122.65%
557.xz_r
100.00%
99.89%
101.89%
100.00%
102.01%
Smaller binary sizes are always better.
Click to display/hide
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 100.00% | 100.83% | 100.00% | 100.83% |
| 502.gcc_r | 100.00% | 100.03% | 100.70% | 100.00% | 100.67% |
| 505.mcf_r | 100.00% | 100.00% | 109.38% | 100.00% | 109.38% |
| 520.omnetpp_r | 100.00% | 99.94% | 101.11% | 100.00% | 101.17% |
| 523.xalancbmk_r | 100.00% | 100.01% | 101.29% | 100.00% | 101.28% |
| 525.x264_r | 100.00% | 97.18% | 97.42% | 100.00% | 100.25% |
| 531.deepsjeng_r | 100.00% | 99.99% | 100.01% | 100.00% | 100.02% |
| 541.leela_r | 100.00% | 100.42% | 101.40% | 100.00% | 100.98% |
| 548.exchange2_r | 100.00% | 99.71% | 122.29% | 100.00% | 122.65% |
| 557.xz_r | 100.00% | 99.89% | 101.89% | 100.00% | 102.01% |