SPECINT 2006: 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
400.perlbench
100.00%
99.59%
98.97%
100.00%
99.38%
401.bzip2
100.00%
100.20%
100.00%
100.00%
99.80%
403.gcc
100.00%
99.39%
99.39%
100.00%
100.00%
429.mcf
100.00%
100.41%
97.36%
100.00%
96.96%
445.gobmk
100.00%
99.60%
99.20%
100.00%
99.60%
456.hmmer
100.00%
89.54%
85.71%
100.00%
95.73%
458.sjeng
100.00%
100.81%
99.59%
100.00%
98.79%
462.libquantum
100.00%
104.49%
88.68%
100.00%
84.87%
464.h264ref
100.00%
98.59%
99.40%
100.00%
100.81%
471.omnetpp
100.00%
98.14%
99.38%
100.00%
101.26%
473.astar
100.00%
100.00%
100.61%
100.00%
100.61%
483.xalancbmk
100.00%
102.92%
101.04%
100.00%
98.18%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 400.perlbench | 100.00% | 99.59% | 98.97% | 100.00% | 99.38% |
| 401.bzip2 | 100.00% | 100.20% | 100.00% | 100.00% | 99.80% |
| 403.gcc | 100.00% | 99.39% | 99.39% | 100.00% | 100.00% |
| 429.mcf | 100.00% | 100.41% | 97.36% | 100.00% | 96.96% |
| 445.gobmk | 100.00% | 99.60% | 99.20% | 100.00% | 99.60% |
| 456.hmmer | 100.00% | 89.54% | 85.71% | 100.00% | 95.73% |
| 458.sjeng | 100.00% | 100.81% | 99.59% | 100.00% | 98.79% |
| 462.libquantum | 100.00% | 104.49% | 88.68% | 100.00% | 84.87% |
| 464.h264ref | 100.00% | 98.59% | 99.40% | 100.00% | 100.81% |
| 471.omnetpp | 100.00% | 98.14% | 99.38% | 100.00% | 101.26% |
| 473.astar | 100.00% | 100.00% | 100.61% | 100.00% | 100.61% |
| 483.xalancbmk | 100.00% | 102.92% | 101.04% | 100.00% | 98.18% |
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
400.perlbench
100.00%
99.94%
100.10%
100.00%
100.16%
401.bzip2
100.00%
100.22%
101.23%
100.00%
101.01%
403.gcc
100.00%
100.01%
100.13%
100.00%
100.12%
429.mcf
100.00%
100.21%
100.38%
100.00%
100.17%
445.gobmk
100.00%
100.00%
99.99%
100.00%
99.99%
456.hmmer
100.00%
99.45%
99.62%
100.00%
100.17%
458.sjeng
100.00%
100.00%
100.03%
100.00%
100.03%
462.libquantum
100.00%
98.95%
98.60%
100.00%
99.65%
464.h264ref
100.00%
99.78%
101.18%
100.00%
101.41%
471.omnetpp
100.00%
99.82%
100.79%
100.00%
100.97%
473.astar
100.00%
100.18%
99.14%
100.00%
98.96%
483.xalancbmk
100.00%
99.96%
100.75%
100.00%
100.79%
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 |
|---|---|---|---|---|---|
| 400.perlbench | 100.00% | 99.94% | 100.10% | 100.00% | 100.16% |
| 401.bzip2 | 100.00% | 100.22% | 101.23% | 100.00% | 101.01% |
| 403.gcc | 100.00% | 100.01% | 100.13% | 100.00% | 100.12% |
| 429.mcf | 100.00% | 100.21% | 100.38% | 100.00% | 100.17% |
| 445.gobmk | 100.00% | 100.00% | 99.99% | 100.00% | 99.99% |
| 456.hmmer | 100.00% | 99.45% | 99.62% | 100.00% | 100.17% |
| 458.sjeng | 100.00% | 100.00% | 100.03% | 100.00% | 100.03% |
| 462.libquantum | 100.00% | 98.95% | 98.60% | 100.00% | 99.65% |
| 464.h264ref | 100.00% | 99.78% | 101.18% | 100.00% | 101.41% |
| 471.omnetpp | 100.00% | 99.82% | 100.79% | 100.00% | 100.97% |
| 473.astar | 100.00% | 100.18% | 99.14% | 100.00% | 98.96% |
| 483.xalancbmk | 100.00% | 99.96% | 100.75% | 100.00% | 100.79% |
Intel Cascade Lake Xeon
Run-times
Benchmark
x86-64
x86-64-v2
x86-64-v3
x86-64-v2
x86-64-v3
400.perlbench
100.00%
99.19%
99.60%
100.00%
100.41%
401.bzip2
100.00%
100.21%
102.28%
100.00%
102.07%
403.gcc
100.00%
100.61%
100.61%
100.00%
100.00%
429.mcf
100.00%
100.61%
97.56%
100.00%
96.97%
445.gobmk
100.00%
100.40%
100.00%
100.00%
99.60%
456.hmmer
100.00%
103.33%
102.49%
100.00%
99.20%
458.sjeng
100.00%
100.61%
101.43%
100.00%
100.81%
462.libquantum
100.00%
101.57%
92.84%
100.00%
91.41%
464.h264ref
100.00%
96.39%
95.98%
100.00%
99.58%
471.omnetpp
100.00%
100.61%
100.00%
100.00%
99.39%
473.astar
100.00%
100.00%
101.24%
100.00%
101.24%
483.xalancbmk
100.00%
101.63%
101.63%
100.00%
100.00%
| Benchmark | x86-64 | x86-64-v2 | x86-64-v3 | x86-64-v2 | x86-64-v3 |
|---|---|---|---|---|---|
| 400.perlbench | 100.00% | 99.19% | 99.60% | 100.00% | 100.41% |
| 401.bzip2 | 100.00% | 100.21% | 102.28% | 100.00% | 102.07% |
| 403.gcc | 100.00% | 100.61% | 100.61% | 100.00% | 100.00% |
| 429.mcf | 100.00% | 100.61% | 97.56% | 100.00% | 96.97% |
| 445.gobmk | 100.00% | 100.40% | 100.00% | 100.00% | 99.60% |
| 456.hmmer | 100.00% | 103.33% | 102.49% | 100.00% | 99.20% |
| 458.sjeng | 100.00% | 100.61% | 101.43% | 100.00% | 100.81% |
| 462.libquantum | 100.00% | 101.57% | 92.84% | 100.00% | 91.41% |
| 464.h264ref | 100.00% | 96.39% | 95.98% | 100.00% | 99.58% |
| 471.omnetpp | 100.00% | 100.61% | 100.00% | 100.00% | 99.39% |
| 473.astar | 100.00% | 100.00% | 101.24% | 100.00% | 101.24% |
| 483.xalancbmk | 100.00% | 101.63% | 101.63% | 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
400.perlbench
100.00%
99.94%
100.10%
100.00%
100.16%
401.bzip2
100.00%
100.22%
101.23%
100.00%
101.01%
403.gcc
100.00%
100.01%
100.13%
100.00%
100.12%
429.mcf
100.00%
100.21%
100.38%
100.00%
100.17%
445.gobmk
100.00%
100.00%
99.99%
100.00%
99.99%
456.hmmer
100.00%
99.45%
99.62%
100.00%
100.17%
458.sjeng
100.00%
100.00%
100.03%
100.00%
100.03%
462.libquantum
100.00%
98.95%
98.60%
100.00%
99.65%
464.h264ref
100.00%
99.78%
101.18%
100.00%
101.41%
471.omnetpp
100.00%
99.82%
100.79%
100.00%
100.97%
473.astar
100.00%
100.18%
99.14%
100.00%
98.96%
483.xalancbmk
100.00%
99.96%
100.75%
100.00%
100.79%
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 |
|---|---|---|---|---|---|
| 400.perlbench | 100.00% | 99.94% | 100.10% | 100.00% | 100.16% |
| 401.bzip2 | 100.00% | 100.22% | 101.23% | 100.00% | 101.01% |
| 403.gcc | 100.00% | 100.01% | 100.13% | 100.00% | 100.12% |
| 429.mcf | 100.00% | 100.21% | 100.38% | 100.00% | 100.17% |
| 445.gobmk | 100.00% | 100.00% | 99.99% | 100.00% | 99.99% |
| 456.hmmer | 100.00% | 99.45% | 99.62% | 100.00% | 100.17% |
| 458.sjeng | 100.00% | 100.00% | 100.03% | 100.00% | 100.03% |
| 462.libquantum | 100.00% | 98.95% | 98.60% | 100.00% | 99.65% |
| 464.h264ref | 100.00% | 99.78% | 101.18% | 100.00% | 101.41% |
| 471.omnetpp | 100.00% | 99.82% | 100.79% | 100.00% | 100.97% |
| 473.astar | 100.00% | 100.18% | 99.14% | 100.00% | 98.96% |
| 483.xalancbmk | 100.00% | 99.96% | 100.75% | 100.00% | 100.79% |