[03:07] *** vrurg joined [03:07] *** vrurg_ left [10:59] aw yeah, first WIP draft of moarvm with [[clang::musttail]] interpreter just linked without spowing errors [11:06] well, NQP already seems to work, but extops are broken at this moment [11:07] but the first benefit is, when stepping backwards in the interpreter with rr i just "reverse-finish" and it just jumps me to the "GOTO_NEXT_OP" in whatever was the previous opcode and that's fucking fantastic [11:40] mysteriously, the nqp test suite is all green except for the qast tests which mostly fail :D [11:44] i wonder if there is something like "finish" that steps to the next tail call, to mirror what reverse-finish does with our tailcall based interpreter [12:18] "make test" is clean (plus/minus the usual) [12:18] i kind of hate that we have a "the usual test failures" [12:53] we currently have a cur_op, reg_base, cu, and bytecode_start local on the MVM_interp_run stack frame that the TC is pointed at which some operations manipulate in order to redirect the interpreter (frame invokes and returns and what-not) which in order to keep around from one interp op function to the next would have to be passed as a pointer to the place on the stack where they were set up [12:54] but that's not exactly optimal in terms of performance I think? [12:58] we do have a list of "every op that can invoke" which we could in theory use to put a "get new values if they changed" and keep passing the values themselves in registers? [12:58] that's kind of what the JIT already has to do [13:13] already possibly the tiniest bit faster than CGOTO at core setting compilation [13:13] 49.443 +- 0.174 vs 49.171 +- 0.237 [13:13] (averaged from 4 runs) [13:17] 401,285,398 L1-icache-load-misses vs 188,166,117 L1-icache-load-misses [13:22] ok but this is also a moarvm built with gcc except for the one file, interp.c, which i used clang for because gcc doesn't seem to have __attribute__((preserve_none)) which it sounds like is very important for getting actually small function bodies for the ops themselves (otherwise there's a lot of writing registers to the stack and restoring them etc etc) [13:50] huh. passing around a pointer to a struct that has the variables in it is not any better than passing three pointer-pointers; it would be great if somehow I could make it realize that these variables could really be stack-relative, but the stack frames have to be "compatible" [14:24] i thought "the jit already has to do these checks" but it turns out we optimized this out in a clever way with the "jit trampoline" [15:01] hrmpf. so that failed ... [15:21] *** linkable6 left [15:21] *** coverable6__ left [15:21] *** huggable6 left [15:21] *** evalable6 left [15:21] *** releasable6 left [15:21] *** shareable6 left [15:21] *** quotable6 left [15:21] *** notable6 left [15:21] *** bisectable6 left [15:21] *** bloatable6 left [15:21] *** unicodable6 left [15:21] *** committable6 left [15:21] *** tellable6 left [15:21] *** sourceable6 left [15:21] *** benchable6 left [15:21] *** greppable6 left [15:21] *** nativecallable6 left [15:23] *** nativecallable6 joined [15:24] *** tellable6 joined [15:24] *** bisectable6 joined [15:24] *** committable6 joined [15:25] *** benchable6 joined [15:25] *** releasable6 joined [15:25] *** evalable6 joined [15:25] *** unicodable6 joined [15:25] *** greppable6 joined [15:25] *** huggable6 joined [15:25] *** coverable6 joined [15:25] *** shareable6 joined [15:25] *** quotable6 joined [15:25] *** linkable6 joined [15:25] *** bloatable6 joined [15:26] *** notable6 joined [15:26] *** sourceable6 joined [16:56] ¦ MoarVM/tail_call_interpreter: 5a457ae4b3 | (Timo Paulssen)++ | 7 files [16:56] ¦ MoarVM/tail_call_interpreter: Tail-Call style for interp.c [16:56] ¦ MoarVM/tail_call_interpreter: review: https://github.com/MoarVM/MoarVM/commit/5a457ae4b3 [17:00] ¦ MoarVM: timo++ created pull request #1999: Tail-Call style for interp.c [17:00] ¦ MoarVM: review: https://github.com/MoarVM/MoarVM/pull/1999 [17:04] MasterDuke17 may find this to be vindication maybe :) [17:18] OK, i'm off o/ [18:46] *** lizmat left [18:46] *** lizmat joined [18:50] thanks Timo! Was nice to have you over :-) [19:09] glad to have been there :) [19:09] made it safely back home