SPEC Benchmark CINT95rate Summary Base Base Base Peak Peak Peak Benchmarks # Copies Run Time Rate # Copies Run Time Rate ------------ -------- -------- -------- -------- -------- -------- 099.go 2 842 98.4 4 1604 103 124.m88ksim 2 526 65.0 4 980 69.8 126.gcc 2 389 78.8 4 771 79.4 129.compress 2 382 84.8 4 725 89.3 130.li 2 400 85.5 4 752 90.9 132.ijpeg 2 602 71.7 4 1224 70.6 134.perl 2 455 75.2 4 863 79.3 147.vortex 2 709 68.5 4 1483 65.5 SPECint_rate_base95 (G. M.) 77.9 SPECint_rate95 (Geom. Mean) 80.1 HARDWARE -------- Model Name: RM600-720 CPU: 250 MHz R4400 FPU: Integrated Number of CPU(s): 2 Primary Cache: 16KBI+16KBD on chip Secondary Cache: 4MB(I+D) off chip per CPU Other Cache: None Memory: 256MB Disk Subsystem: 16 x 2 GB (striped) Other Hardware: None SOFTWARE -------- Operating System: SINIX-Y V5.43 B 00 Compiler: C-DS V1.1A File System: UFS (/tmp as RAM disk) System State: Multi User NOTES ------- Baseline, all benchmarks: -O4 -Knopic Peak flags: 099: -O4 -Knopic -WM,-G1799 -Wc,-afep,3 124: -O4 -Knopic -Wm,-i,"m88ksim-5-24.fb" 126: -O4 -Kold -WM,-G16 -Knoinline -Krostr -Kroconst -Wc,-afep,4 129: -O4 -Kold -WM,-G1599 -Krostr -Kroconst -Wm,-i,"compress-7-8.fb" 130: -O4 -Knopic -WM,-G1599 -Wm,-i,"li-10-20.fb" 132: -O4 -Kold -WM,-G1599 -Wo,-docodehoist -Wm,-i,"ijpeg-5-20.fb" 134: -O4 -Knopic 147: -O4 -Kold -WM,-G4 -Krostr -Kroconst Feedback-directed optimization is used for benchmarks 124, 129, 130, 132 Complete compiler/feedback invocation in these cases: PASS1_CFLAGS = ... -qp fdo_post1 = /opt/C/bin/make_freq_inline_pos -p %binary% -m mon.out n1 n2 | tee /tmp/%benchname%.n1.n2.fb PASS2_CFLAGS = ... -Wm,-i,"/tmp/%benchname%.n1.n2.fb"