aboutsummaryrefslogtreecommitdiff
path: root/gcc/cse.cc
diff options
context:
space:
mode:
authorRichard Biener <rguenther@suse.de>2023-02-03 11:11:15 +0100
committerRichard Biener <rguenther@suse.de>2023-05-03 12:21:30 +0200
commit2961db432ebb11d72c1438f44a59529a32b835cd (patch)
treeb04b5b677e4114ae9ae87bf0e01fc2b782dc9996 /gcc/cse.cc
parentaeeec83b0e26edf43e1460d2e85f62cb9bc57439 (diff)
downloadgcc-2961db432ebb11d72c1438f44a59529a32b835cd.zip
gcc-2961db432ebb11d72c1438f44a59529a32b835cd.tar.gz
gcc-2961db432ebb11d72c1438f44a59529a32b835cd.tar.bz2
Speedup cse_insn
When cse_insn prunes src{,_folded,_eqv_here,_related} with the equivalence set in the *_same_value chain it also searches for an equivalence to the destination of the instruction with /* This is the same as the destination of the insns, we want to prefer it. Copy it to src_related. The code below will then give it a negative cost. */ if (GET_CODE (dest) == code && rtx_equal_p (p->exp, dest)) src_related = p->exp; this picks up the last such equivalence and in particular any later duplicate will be pruned by the preceeding else if (src_related && GET_CODE (src_related) == code && rtx_equal_p (src_related, p->exp)) src_related = 0; first. This wastes cycles doing extra rtx_equal_p checks. The following instead searches for the first destination equivalence separately in this loop and delays using src_related for it until we are about to process that, avoiding another redundant rtx_equal_p check. I've came here because of a testcase with very large equivalence lists and compile-time of cse_insn. The patch below doesn't speed it up significantly since there's no equivalence on the destination. In theory this opens the possibility to track dest_related separately, avoiding the implicit pruning of any previous value in src_related. As is the change should be a no-op for code generation. * cse.cc (cse_insn): Track an equivalence to the destination separately and delay using src_related for it.
Diffstat (limited to 'gcc/cse.cc')
-rw-r--r--gcc/cse.cc51
1 files changed, 27 insertions, 24 deletions
diff --git a/gcc/cse.cc b/gcc/cse.cc
index c2c1729..b10c9b0 100644
--- a/gcc/cse.cc
+++ b/gcc/cse.cc
@@ -4623,6 +4623,7 @@ cse_insn (rtx_insn *insn)
rtx src_eqv_here;
rtx src_const = 0;
rtx src_related = 0;
+ rtx dest_related = 0;
bool src_related_is_const_anchor = false;
struct table_elt *src_const_elt = 0;
int src_cost = MAX_COST;
@@ -5094,10 +5095,11 @@ cse_insn (rtx_insn *insn)
src_related = 0;
/* This is the same as the destination of the insns, we want
- to prefer it. Copy it to src_related. The code below will
- then give it a negative cost. */
- if (GET_CODE (dest) == code && rtx_equal_p (p->exp, dest))
- src_related = p->exp;
+ to prefer it. The code below will then give it a negative
+ cost. */
+ if (!dest_related
+ && GET_CODE (dest) == code && rtx_equal_p (p->exp, dest))
+ dest_related = p->exp;
}
/* Find the cheapest valid equivalent, trying all the available
@@ -5139,27 +5141,28 @@ cse_insn (rtx_insn *insn)
}
}
- if (src_related)
+ if (dest_related)
{
- if (rtx_equal_p (src_related, dest))
- src_related_cost = src_related_regcost = -1;
- else
- {
- src_related_cost = COST (src_related, mode);
- src_related_regcost = approx_reg_cost (src_related);
-
- /* If a const-anchor is used to synthesize a constant that
- normally requires multiple instructions then slightly prefer
- it over the original sequence. These instructions are likely
- to become redundant now. We can't compare against the cost
- of src_eqv_here because, on MIPS for example, multi-insn
- constants have zero cost; they are assumed to be hoisted from
- loops. */
- if (src_related_is_const_anchor
- && src_related_cost == src_cost
- && src_eqv_here)
- src_related_cost--;
- }
+ src_related_cost = src_related_regcost = -1;
+ /* Handle it as src_related. */
+ src_related = dest_related;
+ }
+ else if (src_related)
+ {
+ src_related_cost = COST (src_related, mode);
+ src_related_regcost = approx_reg_cost (src_related);
+
+ /* If a const-anchor is used to synthesize a constant that
+ normally requires multiple instructions then slightly prefer
+ it over the original sequence. These instructions are likely
+ to become redundant now. We can't compare against the cost
+ of src_eqv_here because, on MIPS for example, multi-insn
+ constants have zero cost; they are assumed to be hoisted from
+ loops. */
+ if (src_related_is_const_anchor
+ && src_related_cost == src_cost
+ && src_eqv_here)
+ src_related_cost--;
}
/* If this was an indirect jump insn, a known label will really be