vs

 1 : Are the Erlang HiPE programs faster? At a glance.

Each chart bar shows, for one unidentified benchmark, how much the fastest Erlang HiPE program used compared to the fastest Java program.

(Memory use is only compared for tasks that require memory to be allocated.)


These are not the only compilers and interpreters. These are not the only programs that could be written. These are not the only tasks that could be solved. These are just 10 tiny examples.

 2 : Are the Erlang HiPE programs faster? Approximately.

Each table row shows, for one named benchmark, how much the fastest Erlang HiPE program used compared to the fastest Java program.

(Memory use is only compared for tasks that require memory to be allocated.)

 Erlang HiPE used what fraction? used how many times more? 
Benchmark Time Memory Code
 binary-trees±
 spectral-norm ±
 pidigits 1/2
 n-body ±
 regex-dna1/2±
 reverse-complement±
 fannkuch-redux ±
 mandelbrot11× ±
 fasta †13× 1/2
 k-nucleotide14×±1/2
 Erlang HiPE used what fraction? used how many times more? 
Time-used  |-  |---  25% median  75%  ---|  -|
(Elapsed secs)11×14×14×

† possible mismatch - one-core program compared to multi-core program.

± read the measurements and then read the program source code.

 3 : Are the Erlang HiPE programs faster? Measurements.

These are not the only tasks that could be solved. These are just 10 tiny examples. These are not the only compilers and interpreters. These are not the only programs that could be written.

For each named benchmark, measurements of the fastest Erlang HiPE program are shown for comparison against measurements of the fastest Java program.

Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
 binary-trees 
Erlang HiPE69.7228.011,028,396499  52% 57% 47% 95%
Java24.8914.48390,708584  34% 73% 38% 30%
 spectral-norm 
Erlang HiPE47.4812.0922,836747  99% 98% 98% 98%
Java17.804.5921,132950  97% 96% 99% 96%
 pidigits 
Erlang HiPE16.4715.5727,604512  1% 5% 99% 1%
Java3.173.0323,504938  19% 80% 5% 3%
 n-body 
Erlang HiPE125.85125.8813,1441399  79% 21% 0% 0%
Java22.9022.8719,5721424  99% 1% 1% 1%
 regex-dna 
Erlang HiPE182.8147.68337,0961058  92% 96% 99% 97%
Java24.528.59707,744929  80% 64% 79% 64%
 reverse-complement 
Erlang HiPE19.939.98975,1241302  32% 33% 57% 80%
Java2.971.47300,7121661  47% 37% 78% 43%
 fannkuch-redux 
Erlang HiPE493.55125.7312,8721038  99% 100% 97% 97%
Java70.0617.7319,7201282  99% 99% 98% 99%
 mandelbrot 
Erlang HiPE274.0377.841,269,512534  88% 96% 85% 84%
Java27.847.1162,344796  98% 97% 98% 100%
 fasta 
Erlang HiPE29.4329.4314,1641164  86% 0% 14% 0% †
Java5.782.2032,6202457  62% 75% 63% 65% †
 k-nucleotide 
Erlang HiPE376.69143.111,133,724932  68% 78% 64% 60%
Java34.4410.221,096,5401844  79% 83% 82% 94%
 fasta-redux 
No program
Java0.210.17?1443  11% 6% 89% 17%

† possible mismatch - one-core program compared to multi-core program.

 4 : Are there other Erlang HiPE programs for these benchmarks?

Remember - those are just the fastest Erlang HiPE and Java programs measured on this OS/machine. Check if there are other implementations of these benchmark programs for Erlang HiPE.

Maybe one of those other Erlang HiPE programs is fastest on a different OS/machine.

 5 : Are there other faster programs for these benchmarks?

Remember - those are just the fastest Erlang HiPE and Java programs measured on this OS/machine. Check if there are faster implementations of these benchmark programs for other programming languages.

Maybe one of those other programs is fastest on a different OS/machine.

 Erlang HiPE : concurrent real-time distributed fault-tolerant software 

"Four-fold Increase in Productivity and Quality: Industrial-Strength Functional Programming in Telecom-Class Products" pdf

All you wanted to know about the HiPE compile (but might have been afraid to ask)

The development of the HiPE system: design and experience report

Erlang R16B (erts-5.10.1) [source] [64-bit] [smp:4:4] [async-threads:10] [hipe] [kernel-poll:false]

Home Page: http://www.erlang.org/

Download: http://www.erlang.org/download.html

Revised BSD license

  Home   Conclusions   License   Play