SPEC CPU result comparison

15th October 2026 - Normalized report

SPEC2026 INTrate: PGO generic -O2 - Released GCCs vs Trunk

-O2 -fprofile-use

AMD EPYC 8635P (zen5 based Sorano)

Run-times

Benchmark GCC 16 Trunk
706.stockfish_r 100.00% 89.27%
707.ntest_r 100.00% 97.97%
708.sqlite_r 100.00% 100.67%
710.omnetpp_r 100.00% 101.25%
714.cpython_r 100.00% 100.00%
721.gcc_r 100.00% 99.35%
723.llvm_r 100.00% 101.36%
727.cppcheck_r 100.00% 103.51%
729.abc_r 100.00% 98.34%
734.vpr_r 100.00% 100.00%
735.gem5_r 100.00% 98.19%
750.sealcrypto_r 100.00% 50.71%
753.ns3_r 100.00% 100.82%
777.zstd_r 100.00% 100.00%
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% 100.90%
707.ntest_r 100.00% 99.12%
708.sqlite_r 100.00% 99.31%
710.omnetpp_r 100.00% 100.42%
714.cpython_r 100.00% 99.99%
721.gcc_r 100.00% 100.39%
723.llvm_r 100.00% 99.68%
727.cppcheck_r 100.00% 99.46%
729.abc_r 100.00% 100.01%
734.vpr_r 100.00% 100.21%
735.gem5_r 100.00% 101.19%
750.sealcrypto_r 100.00% 98.70%
753.ns3_r 100.00% 100.15%
777.zstd_r 100.00% 99.88%
Smaller binary sizes are always better.