Skip to content

Instantly share code, notes, and snippets.

@jauderho
Created June 18, 2010 09:21
Show Gist options
  • Save jauderho/443429 to your computer and use it in GitHub Desktop.
Save jauderho/443429 to your computer and use it in GitHub Desktop.
# Pixi (ka6sox)
# @ 600mhz - warthog
2007 ARM toolchain - Unrolled Single Precision 55730 Kflops ; 100 Reps
# @ 600mhz - stock
2007 ARM toolchain - Unrolled Single Precision 55229 Kflops ; 100 Reps
# Sprint Pre (unixpsycho)
# @ 1050mhz (compiled with -Os -mcpu=cortex-a8 -mtune=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=softfp)
2007 ARM toolchain - Unrolled Single Precision 50490 Kflops ; 100 Reps
# @ 1200mhz
2007 ARM toolchain - Unrolled Single Precision 58192 Kflops ; 100 Reps
#
# Sprint Pre running screenstate 500/720mhz
#
# @ 720mhz (compiled with -Os -mcpu=cortex-a8 -mtune=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=softfp)
2010 ARM toolchain - Unrolled Single Precision 26109 Kflops ; 100 Reps
2007 ARM toolchain - Unrolled Single Precision 34680 Kflops ; 100 Reps
# @ 500mhz (compiled with -Os -mcpu=cortex-a8 -mtune=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=softfp)
2010 ARM toolchain - Unrolled Single Precision 18659 Kflops ; 100 Reps
2007 ARM toolchain - Unrolled Single Precision 23760 Kflops ; 100 Reps
# @ 500mhz (compiled with -Os only)
2007 ARM toolchain - Unrolled Single Precision 12740 Kflops ; 100 Reps
# @ 500mhz (compiled with no opt flags)
2007 ARM toolchain - Unrolled Single Precision 8918 Kflops ; 100 Reps
# @ 500mhz (compiled with -O2 -mcpu=cortex-a8 -mtune=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=softfp)
2010 ARM toolchain - Unrolled Single Precision 15362 Kflops ; 100 Reps
2007 ARM toolchain - Unrolled Single Precision 24264 Kflops ; 100 Reps
# @ 500mhz (compiled with -O3 -mcpu=cortex-a8 -mtune=cortex-a8 -march=armv7-a -mfpu=neon -mfloat-abi=softfp)
2010 ARM toolchain - Unrolled Single Precision 15677 Kflops ; 100 Reps
2007 ARM toolchain - Unrolled Single Precision 24178 Kflops ; 100 Reps
# @ 500mhz (compiled with -O3 -funroll-loops -fgcse-sm -falign-loops=8 -march=armv7-a -mcpu=cortex-a8 -combine -mfloat-abi=soft -ftree-vectorize -ftree-vectorizer-verbose=1 -mfpu=neon -static -fomit-frame-pointer -lrt)
2010 ARM toolchain - Unrolled Single Precision 11220 Kflops ; 100 Reps
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment