|
00:35
colomon_ joined
00:36
colomon left,
colomon_ is now known as colomon
|
|||
| samcv | what was that ENV variable that when set makes benchmarking more reproducible? | 01:00 | |
| MasterDuke | MVM_SPESH_BLOCKING | 01:14 | |
| samcv: ^^^ | 01:16 | ||
|
01:46
ilbot3 left
01:57
ilbot3 joined
|
|||
| MasterDuke | weird. i can perf record a regular rakudo CORE.setting compile, but if i change it to --target=parse, it pretty much goes on forever, creating a bigger and bigger data file | 02:54 | |
| in the regular compile, the top function is MVM_interp_run at only 7.25%. however, in the target=parse case, the top two functions are MVM_gc_root_add_frame_registers_to_worklist and MVM_gc_root_add_frame_roots_to_worklist which are 38% and 12.3% respectively | 03:00 | ||
| samcv | maybe i could hide it behind some define that we set if we're ok with unaligned memory accesses | 03:22 | |
| and then i can hide the 32 bit aligned 64 bit integer access i use on 64 bit platforms behind that as well | |||
|
06:53
domidumont joined
06:59
domidumont left
07:00
domidumont joined
|
|||
| nine | samcv: yes, making it optional seems like the way to go | 08:27 | |
|
09:12
lizmat left
09:26
lizmat joined
10:49
lizmat left
11:45
avar left,
avar joined
12:11
lizmat joined
12:18
lizmat left
12:32
lizmat joined
12:40
bisectable6 left,
evalable6 left,
committable6 left,
bisectable6 joined,
evalable6 joined,
committable6 joined
12:46
lizmat left
12:51
lizmat joined
13:39
lizmat left
13:46
lizmat joined
13:50
lizmat left
14:26
domidumont left
|
|||
| Geth | MoarVM/master: 5 commits pushed by (Stefan Seifert)++ | 15:04 | |
|
18:11
domidumont joined
19:07
lizmat joined
19:09
benchable6 left,
benchable6 joined,
buggable left
19:10
huggable left,
ZofBot left
19:12
hoelzro left,
leedo left,
hoelzro joined,
leedo joined
19:13
domidumont left
20:07
squashable6 left,
squashable6 joined
20:09
lizmat left
20:23
brrt joined
|
|||
| brrt | .tell nine i'm suspicious of encoderepconf. I know that's what interp.c does, but it is not what oplist says | 20:24 | |
| yoleaux | brrt: I'll pass your message to nine. | ||
| brrt | oplist says "encoderepconf w(obj) r(str) r(str) r(str) r(obj) r(int64)" - which means that the zeroth argument should be the one written to | 20:28 | |
| also, because of this, the expr template will do the wrong thing; it will try to assign to the object address, not to the variable slot | |||
| $4 will be the pointer, not the address-of-the-work address | 20:29 | ||
| anyway, that's all i have. see you around | 20:30 | ||
|
20:30
brrt left
20:40
undersightable6 left
20:42
undersightable6 joined
20:45
zakharyas joined
20:51
evalable6 left,
evalable6 joined
20:55
Kaiepi left
20:57
Kaiepi joined
21:55
Kaypie joined
21:56
Kaiepi left
22:00
lizmat joined
22:02
Kaypie left
22:10
zakharyas left
22:13
Kaiepi joined
22:25
Kaiepi left
22:41
Kaiepi joined
22:55
Kaiepi left
22:56
Kaiepi joined
23:33
Kaiepi left
|
|||