SPEC2017 INTrate: LTO -O2 - Different x86_64 levels
-flto -O2
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%
99.19%
100.40%
100.00%
101.22%
502.gcc_r
100.00%
100.00%
99.40%
100.00%
99.40%
505.mcf_r
100.00%
100.00%
100.00%
100.00%
100.00%
520.omnetpp_r
100.00%
97.35%
98.78%
100.00%
101.46%
523.xalancbmk_r
100.00%
100.62%
103.53%
100.00%
102.89%
525.x264_r
100.00%
99.40%
98.19%
100.00%
98.78%
531.deepsjeng_r
100.00%
96.15%
93.91%
100.00%
97.68%
541.leela_r
100.00%
98.80%
100.00%
100.00%
101.22%
548.exchange2_r
100.00%
100.00%
101.02%
100.00%
101.02%
557.xz_r
100.00%
101.85%
102.26%
100.00%
100.40%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 99.19% | 100.40% | 100.00% | 101.22% |
| 502.gcc_r | 100.00% | 100.00% | 99.40% | 100.00% | 99.40% |
| 505.mcf_r | 100.00% | 100.00% | 100.00% | 100.00% | 100.00% |
| 520.omnetpp_r | 100.00% | 97.35% | 98.78% | 100.00% | 101.46% |
| 523.xalancbmk_r | 100.00% | 100.62% | 103.53% | 100.00% | 102.89% |
| 525.x264_r | 100.00% | 99.40% | 98.19% | 100.00% | 98.78% |
| 531.deepsjeng_r | 100.00% | 96.15% | 93.91% | 100.00% | 97.68% |
| 541.leela_r | 100.00% | 98.80% | 100.00% | 100.00% | 101.22% |
| 548.exchange2_r | 100.00% | 100.00% | 101.02% | 100.00% | 101.02% |
| 557.xz_r | 100.00% | 101.85% | 102.26% | 100.00% | 100.40% |
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%
99.96%
100.02%
100.00%
100.05%
502.gcc_r
100.00%
99.98%
100.21%
100.00%
100.23%
505.mcf_r
100.00%
100.09%
100.78%
100.00%
100.69%
520.omnetpp_r
100.00%
99.92%
100.53%
100.00%
100.61%
523.xalancbmk_r
100.00%
99.98%
100.61%
100.00%
100.63%
525.x264_r
100.00%
99.48%
99.37%
100.00%
99.89%
531.deepsjeng_r
100.00%
99.99%
99.99%
100.00%
100.00%
541.leela_r
100.00%
99.99%
100.96%
100.00%
100.97%
548.exchange2_r
100.00%
100.00%
102.38%
100.00%
102.38%
557.xz_r
100.00%
99.97%
100.03%
100.00%
100.06%
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% | 99.96% | 100.02% | 100.00% | 100.05% |
| 502.gcc_r | 100.00% | 99.98% | 100.21% | 100.00% | 100.23% |
| 505.mcf_r | 100.00% | 100.09% | 100.78% | 100.00% | 100.69% |
| 520.omnetpp_r | 100.00% | 99.92% | 100.53% | 100.00% | 100.61% |
| 523.xalancbmk_r | 100.00% | 99.98% | 100.61% | 100.00% | 100.63% |
| 525.x264_r | 100.00% | 99.48% | 99.37% | 100.00% | 99.89% |
| 531.deepsjeng_r | 100.00% | 99.99% | 99.99% | 100.00% | 100.00% |
| 541.leela_r | 100.00% | 99.99% | 100.96% | 100.00% | 100.97% |
| 548.exchange2_r | 100.00% | 100.00% | 102.38% | 100.00% | 102.38% |
| 557.xz_r | 100.00% | 99.97% | 100.03% | 100.00% | 100.06% |
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%
99.40%
100.00%
100.00%
100.61%
502.gcc_r
100.00%
100.40%
99.60%
100.00%
99.19%
505.mcf_r
100.00%
97.77%
99.19%
100.00%
101.45%
520.omnetpp_r
100.00%
97.53%
97.94%
100.00%
100.42%
523.xalancbmk_r
100.00%
96.79%
98.59%
100.00%
101.87%
525.x264_r
100.00%
100.00%
97.78%
100.00%
97.78%
531.deepsjeng_r
100.00%
95.67%
92.37%
100.00%
96.55%
541.leela_r
100.00%
99.59%
101.22%
100.00%
101.63%
548.exchange2_r
100.00%
100.00%
101.43%
100.00%
101.43%
557.xz_r
100.00%
102.74%
102.32%
100.00%
99.59%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 500.perlbench_r | 100.00% | 99.40% | 100.00% | 100.00% | 100.61% |
| 502.gcc_r | 100.00% | 100.40% | 99.60% | 100.00% | 99.19% |
| 505.mcf_r | 100.00% | 97.77% | 99.19% | 100.00% | 101.45% |
| 520.omnetpp_r | 100.00% | 97.53% | 97.94% | 100.00% | 100.42% |
| 523.xalancbmk_r | 100.00% | 96.79% | 98.59% | 100.00% | 101.87% |
| 525.x264_r | 100.00% | 100.00% | 97.78% | 100.00% | 97.78% |
| 531.deepsjeng_r | 100.00% | 95.67% | 92.37% | 100.00% | 96.55% |
| 541.leela_r | 100.00% | 99.59% | 101.22% | 100.00% | 101.63% |
| 548.exchange2_r | 100.00% | 100.00% | 101.43% | 100.00% | 101.43% |
| 557.xz_r | 100.00% | 102.74% | 102.32% | 100.00% | 99.59% |
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%
99.96%
100.02%
100.00%
100.05%
502.gcc_r
100.00%
99.98%
100.21%
100.00%
100.23%
505.mcf_r
100.00%
100.09%
100.78%
100.00%
100.69%
520.omnetpp_r
100.00%
99.92%
100.53%
100.00%
100.61%
523.xalancbmk_r
100.00%
99.98%
100.61%
100.00%
100.63%
525.x264_r
100.00%
99.48%
99.37%
100.00%
99.89%
531.deepsjeng_r
100.00%
99.99%
99.99%
100.00%
100.00%
541.leela_r
100.00%
99.99%
100.96%
100.00%
100.97%
548.exchange2_r
100.00%
100.00%
102.38%
100.00%
102.38%
557.xz_r
100.00%
99.97%
100.03%
100.00%
100.06%
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% | 99.96% | 100.02% | 100.00% | 100.05% |
| 502.gcc_r | 100.00% | 99.98% | 100.21% | 100.00% | 100.23% |
| 505.mcf_r | 100.00% | 100.09% | 100.78% | 100.00% | 100.69% |
| 520.omnetpp_r | 100.00% | 99.92% | 100.53% | 100.00% | 100.61% |
| 523.xalancbmk_r | 100.00% | 99.98% | 100.61% | 100.00% | 100.63% |
| 525.x264_r | 100.00% | 99.48% | 99.37% | 100.00% | 99.89% |
| 531.deepsjeng_r | 100.00% | 99.99% | 99.99% | 100.00% | 100.00% |
| 541.leela_r | 100.00% | 99.99% | 100.96% | 100.00% | 100.97% |
| 548.exchange2_r | 100.00% | 100.00% | 102.38% | 100.00% | 102.38% |
| 557.xz_r | 100.00% | 99.97% | 100.03% | 100.00% | 100.06% |