On 26 June 2014 05:30, Jeff Law <l...@redhat.com> wrote: > On 06/11/14 04:05, Zhenqiang Chen wrote: >> >> On 10 June 2014 19:06, Steven Bosscher <stevenb....@gmail.com> wrote: >>> >>> On Tue, Jun 10, 2014 at 11:22 AM, Zhenqiang Chen wrote: >>>> >>>> Hi, >>>> >>>> For loop2-invariant pass, when flag_ira_loop_pressure is enabled, >>>> function gain_for_invariant checks the pressures of all register >>>> classes. This does not make sense since one invariant might impact >>>> only one register class. >>>> >>>> The patch enhances functions get_inv_cost and gain_for_invariant to >>>> check only the register pressure of the invariant if possible. >>> >>> >>> This patch may work for targets with more-or-less orthogonal reg >>> classes, but not if there is a lot of overlap between reg classes. >> >> >> Yes. I need check the overlap between reg classes. >> >> Patch is updated to check all overlap reg classes by >> reg_classes_intersect_p: > > So you need a new ChangeLog, of course :-) > > > >> >> diff --git a/gcc/loop-invariant.c b/gcc/loop-invariant.c >> index c76a2a0..6e43b49 100644 >> --- a/gcc/loop-invariant.c >> +++ b/gcc/loop-invariant.c >> @@ -1092,16 +1092,22 @@ get_pressure_class_and_nregs (rtx insn, int >> *nregs) >> } >> >> /* Calculates cost and number of registers needed for moving invariant >> INV >> - out of the loop and stores them to *COST and *REGS_NEEDED. */ >> + out of the loop and stores them to *COST and *REGS_NEEDED. *CL will >> be >> + the REG_CLASS of INV. Return >> + 0: if INV is invalid. >> + 1: if INV and its depends_on have same reg_class >> + > 1: if INV and its depends_on have different reg_classes. */ > > Nit/bikeshedding. I tend to prefer < 0, 0, > 0 (or -1, 0, 1) for > tri-states. It's not a big deal though.
Thanks! Update the tri-state values to ( -1, 0, 1). > >> check_p = i < ira_pressure_classes_num; >> + >> + if ((dep_ret > 1) || ((dep_ret == 1) && (*cl != dep_cl))) >> + { >> + *cl = ALL_REGS; >> + ret ++; > > Whitespace nit -- no space in this statement. use "ret++;" > > You should add a testcase if at all possible. Perhaps two, one which runs > on an ARM variant and one for x86_64. The former because that's obviously > what Linaro cares about, the latter for wider testing. > > > Definitely add a ChangeLog entry, fix the whitespace nit & add testcase. OK > with those fixes. Your choice on the tri-state values. Updated with a testcase for X86-64 and committed @212135. ChangeLog: 2014-06-30 Zhenqiang Chen <zhenqiang.c...@linaro.org> * loop-invariant.c (get_inv_cost): Handle register class. (gain_for_invariant): Check the register pressure of the inv and its overlapped register class, other than all. testsuite/ChangeLog: 2014-06-30 Zhenqiang Chen <zhenqiang.c...@linaro.org> * ira-loop-pressure.c: New test. diff --git a/gcc/loop-invariant.c b/gcc/loop-invariant.c index 25e63e4..ef5c59b 100644 --- a/gcc/loop-invariant.c +++ b/gcc/loop-invariant.c @@ -1090,16 +1090,22 @@ get_pressure_class_and_nregs (rtx insn, int *nregs) } /* Calculates cost and number of registers needed for moving invariant INV - out of the loop and stores them to *COST and *REGS_NEEDED. */ + out of the loop and stores them to *COST and *REGS_NEEDED. *CL will be + the REG_CLASS of INV. Return + -1: if INV is invalid. + 0: if INV and its depends_on have same reg_class + 1: if INV and its depends_on have different reg_classes. */ -static void -get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) +static int +get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed, + enum reg_class *cl) { int i, acomp_cost; unsigned aregs_needed[N_REG_CLASSES]; unsigned depno; struct invariant *dep; bitmap_iterator bi; + int ret = 1; /* Find the representative of the class of the equivalent invariants. */ inv = invariants[inv->eqto]; @@ -1115,7 +1121,7 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) if (inv->move || inv->stamp == actual_stamp) - return; + return -1; inv->stamp = actual_stamp; if (! flag_ira_loop_pressure) @@ -1127,6 +1133,8 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) pressure_class = get_pressure_class_and_nregs (inv->insn, &nregs); regs_needed[pressure_class] += nregs; + *cl = pressure_class; + ret = 0; } if (!inv->cheap_address @@ -1167,6 +1175,8 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) EXECUTE_IF_SET_IN_BITMAP (inv->depends_on, 0, depno, bi) { bool check_p; + enum reg_class dep_cl = ALL_REGS; + int dep_ret; dep = invariants[depno]; @@ -1174,7 +1184,7 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) if (dep->move) continue; - get_inv_cost (dep, &acomp_cost, aregs_needed); + dep_ret = get_inv_cost (dep, &acomp_cost, aregs_needed, &dep_cl); if (! flag_ira_loop_pressure) check_p = aregs_needed[0] != 0; @@ -1184,6 +1194,12 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) if (aregs_needed[ira_pressure_classes[i]] != 0) break; check_p = i < ira_pressure_classes_num; + + if ((dep_ret == 1) || ((dep_ret == 0) && (*cl != dep_cl))) + { + *cl = ALL_REGS; + ret = 1; + } } if (check_p /* We need to check always_executed, since if the original value of @@ -1217,6 +1233,7 @@ get_inv_cost (struct invariant *inv, int *comp_cost, unsigned *regs_needed) } (*comp_cost) += acomp_cost; } + return ret; } /* Calculates gain for eliminating invariant INV. REGS_USED is the number @@ -1231,10 +1248,12 @@ gain_for_invariant (struct invariant *inv, unsigned *regs_needed, bool speed, bool call_p) { int comp_cost, size_cost; + enum reg_class cl; + int ret; actual_stamp++; - get_inv_cost (inv, &comp_cost, regs_needed); + ret = get_inv_cost (inv, &comp_cost, regs_needed, &cl); if (! flag_ira_loop_pressure) { @@ -1243,6 +1262,11 @@ gain_for_invariant (struct invariant *inv, unsigned *regs_needed, - estimate_reg_pressure_cost (new_regs[0], regs_used, speed, call_p)); } + else if (ret < 0) + return -1; + else if ((ret == 0) && (cl == NO_REGS)) + /* Hoist it anyway since it does not impact register pressure. */ + return 1; else { int i; @@ -1251,6 +1275,10 @@ gain_for_invariant (struct invariant *inv, unsigned *regs_needed, for (i = 0; i < ira_pressure_classes_num; i++) { pressure_class = ira_pressure_classes[i]; + + if (!reg_classes_intersect_p (pressure_class, cl)) + continue; + if ((int) new_regs[pressure_class] + (int) regs_needed[pressure_class] + LOOP_DATA (curr_loop)->max_reg_pressure[pressure_class] diff --git a/gcc/testsuite/gcc.dg/ira-loop-pressure.c b/gcc/testsuite/gcc.dg/ira-loop-pressure.c new file mode 100644 index 0000000..7ef4fa7 --- /dev/null +++ b/gcc/testsuite/gcc.dg/ira-loop-pressure.c @@ -0,0 +1,32 @@ +/* Loop2_invariants pass should distinguish register pressures of different + register classes. In this case, register pressue of INT is high. But + we can still move the FP invariant out of the loop. */ + +/* { dg-do compile { target { x86_64-*-* && lp64 } } } */ +/* { dg-options "-O2 -fira-loop-pressure -fdump-rtl-loop2_invariant " } */ + +float tt; +extern void foo2 (int *, int *, int *, int *, int *, int *); +extern int foo3 (int, int, int, int, int, int); +int foo (int a, int b, int c, int d) +{ + int i = a; + int t1, t2, t3, t4, t5, t6; + t1 = t2 = t3 = t4 = t5 = t6 = 0; + + for (; i > 0; i += c) + { + tt += 123456.0; + if (d > t1 + t2) + tt = 3.0; + foo2 (&t1, &t2, &t3, &t4, &t5, &t6); + t1 += t3 + t4 + a + b; + t2 -= t5 - t6 - c - d; + } + + return foo3 (t1, t2, t3, t4, t5, t6); +} + +/* { dg-final { scan-rtl-dump "Decided to move invariant" "loop2_invariant" } } */ +/* { dg-final { cleanup-rtl-dump "loop2_invariant" } } */ +