Post Reply 
Benchmark: Savage
09-30-2018, 11:15 AM (This post was last modified: 09-30-2018 12:03 PM by Albert Chan.)
Post: #9
RE: Benchmark: Savage
(09-30-2018 07:20 AM)StephenG1CMZ Wrote:  Pythonesque version seems about twice as fast as the PPL.

That might explained why Python version is more accurate.

CAS float = 53 bits double, truncated to 48 bits.
Because of truncation, last bit is not as good as round-to-nearest, with slight bias.
Let's say it got effectively 47 bits precision, or about 47/3.322 ~ 14 decimals

PPL is much slower, probably doing BCD math (15 internally, rounded to 12 decimals)

BTW, Python user is more comfortable counting from zero.
For 2499 loops, range(2499) look better than range(1,2500)
Find all posts by this user
Quote this message in a reply
Post Reply 


Messages In This Thread
Benchmark: Savage - StephenG1CMZ - 12-03-2017, 11:40 PM
RE: Benchmark: Savage - StephenG1CMZ - 12-03-2017, 11:42 PM
RE: Benchmark: Savage - StephenG1CMZ - 12-05-2017, 10:51 PM
RE: Benchmark: Savage - StephenG1CMZ - 08-29-2018, 07:37 AM
RE: Benchmark: Savage - StephenG1CMZ - 09-28-2018, 07:20 PM
RE: Benchmark: Savage - StephenG1CMZ - 09-29-2018, 08:16 AM
RE: Benchmark: Savage - Albert Chan - 09-29-2018, 10:47 PM
RE: Benchmark: Savage - StephenG1CMZ - 09-30-2018, 07:20 AM
RE: Benchmark: Savage - Albert Chan - 09-30-2018 11:15 AM
RE: Benchmark: Savage - Albert Chan - 09-30-2018, 02:13 PM
RE: Benchmark: Savage - StephenG1CMZ - 09-30-2018, 04:54 PM
RE: Benchmark: Savage - StephenG1CMZ - 10-12-2018, 09:51 AM
RE: Benchmark: Savage - StephenG1CMZ - 10-12-2018, 10:46 AM
RE: Benchmark: Savage - StephenG1CMZ - 11-01-2018, 08:20 AM



User(s) browsing this thread: 1 Guest(s)