* Question of 2nd instruction scheduling pass
@ 2005-08-12 22:02 Ling-hua Tseng
2005-08-14 0:25 ` James E Wilson
0 siblings, 1 reply; 2+ messages in thread
From: Ling-hua Tseng @ 2005-08-12 22:02 UTC (permalink / raw)
To: gcc
I'm porting gcc-4.0.1 to a new VLIW architecture.
I figured out that the `insn' and `jump_insn' were grouped together in the 2nd sched pass
however there is a `structural hazard' between them.
Such as the following code which generated by gcc -O3 -dP -S code.c:
@(insn:TI 319 315 474 (set (reg/v:SI 7 r7 [orig:107 j.162 ] [107])
@ (const_int 0 [0x0])) 14 {*movsi_const} (nil)
@ (nil))
mov .r0 r7, #0 \\ @ 319 *movsi_const/1 [length = 4]
@(jump_insn 474 319 475 (set (pc)
@ (label_ref 229)) 81 {jump} (nil)
@ (nil))
b <no FU available> .L37 @ 474 jump [length = 4]
I think that the jump_insn must have the TImode, but it don't.
The insn attribute `type' of "*movsi_const" is called "r_dp" (RISC data processing).
The insn attribute `type' of "jump" is called "r_branch" (RISC branch).
The two type of instructions are handled by the same `RISC' function unit (called `r0').
My automata-based pipeline description is also written the following code:
(define_insn_reservation "risc_data_processing" 4
(eq_attr "type" "r_dp")
"r0")
(define_insn_reservation "risc_branch" 0
(eq_attr "type" "r_branch")
"r0")
They should reserved the `r0' (RISC 0) when they're issued.
So they shouldn't be issued in the same cycle however.
Nevertheless, sometimes the jump_insn has the correct mode:
@(insn/f:TI 58 57 59 (set (reg/f:SI 11 r11)
@ (plus:SI (reg:SI 13 r13)
@ (const_int -4 [0xfffffffc]))) 45 {*addsi3} (insn_list:REG_DEP_ANTI 57 (insn_list:REG_DEP_TRUE 56 (nil)))
@ (expr_list:REG_DEAD (reg:SI 13 r13)
@ (nil)))
sub .r0 r11, r13, #4 @ 58 *addsi3/2 [length = 4]
@(jump_insn:TI 17 59 19 (set (pc)
@ (if_then_else (le (reg/v:SI 2 r2 [orig:111 size ] [111])
@ (const_int 0 [0x0]))
@ (label_ref 37)
@ (pc))) 83 {cbranchsi4} (insn_list:REG_DEP_ANTI 56 (insn_list:REG_DEP_ANTI 58 (insn_list:REG_DEP_ANTI 57 (nil))))
@ (expr_list:REG_BR_PROB (const_int 5000 [0x1388])
@ (nil)))
b {!C} .r0 .L11 @ 17 cbranchsi4/1 [length = 4]
I discoverd that the `unconditional branch' is always issued with other insns and the `conditional branch' isn't.
Are there any ways to tell GCC that don't group an jump_insn with other insns when structural hazard occured?
Thanks a lot.
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Question of 2nd instruction scheduling pass
2005-08-12 22:02 Question of 2nd instruction scheduling pass Ling-hua Tseng
@ 2005-08-14 0:25 ` James E Wilson
0 siblings, 0 replies; 2+ messages in thread
From: James E Wilson @ 2005-08-14 0:25 UTC (permalink / raw)
To: Ling-hua Tseng; +Cc: gcc
Ling-hua Tseng wrote:
> Are there any ways to tell GCC that don't group an jump_insn with
> other insns when structural hazard occured?
Probably multiple ways, depending on what exactly the problem is.
I'd suggest using -da -fsched-verbose=2 and looking at the scheduling
info printed in the sched dumps to see what is going on. You should get
a clue to what is wrong there.
You can also try debugging the scheduler code. Grepping for TImode
shows that it is set in schedule_insn in haifa-sched.c, and then you can
work backwards from there to figure out why it doesn't get set in your case.
--
Jim Wilson, GNU Tools Support, http://www.specifix.com
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2005-08-14 0:25 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2005-08-12 22:02 Question of 2nd instruction scheduling pass Ling-hua Tseng
2005-08-14 0:25 ` James E Wilson
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).