SPEC CPU result comparison

15th October 2026 - Normalized report

SPEC2026 INTrate: PGO native -Ofast - Released GCCs vs Trunk

-Ofast -fprofile-use -march=native -mtune=native

Please note that even though the header of this comparison says -Ofast, benchmarks 710.omnetpp_r, 734.vpr_r, 735.gem5_r and 753.ns3_r were additionally compiled with -fno-finite-math-only.

AMD EPYC 8635P (zen5 based Sorano)

Run-times

Benchmark GCC 16 Trunk
706.stockfish_r 100.00% 96.46%
707.ntest_r 100.00% 101.44%
708.sqlite_r 100.00% 98.40%
710.omnetpp_r 100.00% 100.00%
714.cpython_r 100.00% 100.00%
721.gcc_r 100.00% 100.00%
723.llvm_r 100.00% 99.30%
727.cppcheck_r 100.00% 106.09%
729.abc_r 100.00% 101.75%
734.vpr_r 100.00% 100.00%
735.gem5_r 100.00% 100.00%
750.sealcrypto_r 100.00% 58.90%
753.ns3_r 100.00% 100.00%
777.zstd_r 100.00% 101.44%
GCC 15 GCC 15.3.0 (revision 4db0e8df15bef836558857c291c323add11d035c)
GCC 16 GCC 16.2.0 (revision 78d4ac73dd391005b895a6148cd9831e28e1208b)
Trunk GCC 17.0.0 20261015 (experimental) (revision 84348add236100e5f69a3e9ec4f7b1038bf2b83d)
Naturally, the smaller the run-times, the better.
See also continuous gcc branch benchmarking at https://lnt.opensuse.org/db_default/v4/SPEC/spec_report/branch.

Non-debug executable sizes

Benchmark GCC 16 Trunk
706.stockfish_r 100.00% 100.88%
707.ntest_r 100.00% 99.34%
708.sqlite_r 100.00% 98.10%
710.omnetpp_r 100.00% 100.18%
714.cpython_r 100.00% 100.04%
721.gcc_r 100.00% 100.27%
723.llvm_r 100.00% 99.75%
727.cppcheck_r 100.00% 99.41%
729.abc_r 100.00% 99.89%
734.vpr_r 100.00% 99.88%
735.gem5_r 100.00% 100.57%
750.sealcrypto_r 100.00% 97.84%
753.ns3_r 100.00% 100.00%
777.zstd_r 100.00% 100.03%
Smaller binary sizes are always better.