[Issue 5100] -O Degrades performance of loop statements

https://issues.dlang.org/show_bug.cgi?id=5100 Iain Buclaw changed: What|Removed |Added Keywords||backend --

[Issue 5100] -O Degrades performance of loop statements

https://issues.dlang.org/show_bug.cgi?id=5100 --- Comment #10 from Iain Buclaw ibuc...@gdcproject.org --- For a while now I've been thinking that the bottleneck is probably to do with alignment, but I'd have to get out my (now two generations old) atom netbook to investigate further. --

[Issue 5100] -O Degrades performance of loop statements

https://issues.dlang.org/show_bug.cgi?id=5100 Andrei Alexandrescu and...@erdani.com changed: What|Removed |Added Version|D1 D2 |D2 --

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 Walter Bright bugzi...@digitalmars.com changed: What|Removed |Added CC|

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #7 from Iain Buclaw ibuc...@ubuntu.com 2012-01-19 15:33:26 PST --- Maybe not... I actually get the reverse on my new laptop with 2.057, $ dmd loop2.d $ objdump loop2.o -d push %ebp mov%esp,%ebp sub$0x4,%esp movl

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #8 from Iain Buclaw ibuc...@ubuntu.com 2012-01-19 15:39:32 PST --- And on my netbook: $ dmd loop2.d $ time ./loop2 real0m2.948s user0m2.924s sys0m0.012s $ dmd loop2.d -O $ time ./loop2 real0m5.725s user0m5.688s

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #9 from Iain Buclaw ibuc...@ubuntu.com 2012-01-19 15:48:04 PST --- My gut feeling is that the main source of it slowing down is the needless push and pop of the frame pointer. -- Configure issuemail:

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #5 from Iain Buclaw ibuc...@ubuntu.com 2010-12-07 00:59:45 PST --- Been playing about with GCC, this seems to be a better performant: Objdump: push %ebp mov%esp,%ebp and$0xfff0,%esp push %eax sub$0xc,%esp lea

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 Don clugd...@yahoo.com.au changed: What|Removed |Added CC||clugd...@yahoo.com.au ---

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #4 from Iain Buclaw ibuc...@ubuntu.com 2010-12-06 14:51:32 PST --- objdump without -O on Linux: push %ebp mov%esp,%ebp sub$0x4,%esp movl $0x0,-0x4(%ebp) cmpl $0x7fff,-0x4(%ebp) jge1c _Dmain+0x1c addl

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 --- Comment #2 from Stephan Dilly s...@extrawurst.org 2010-12-01 16:51:37 PST --- (In reply to comment #1) for the lazy #5100 is ooops very sorry this comment was meant to be for bug #5294 cause i think it is related. -- Configure

[Issue 5100] -O Degrades performance of loop statements

http://d.puremagic.com/issues/show_bug.cgi?id=5100 Stephan Dilly s...@extrawurst.org changed: What|Removed |Added CC||s...@extrawurst.org