Improve rematerialization costs of addresses. The current costs are set too
high
which results in extra register pressure and spilling. Using lower costs means
addresses will be rematerialized more often rather than being spilled or causing
spills. This results in significant codesize reductions and performance gains.
SPECINT2017 improves by 0.27% with LTO and 0.16% without LTO. Codesize is 0.12%
smaller.
Passes bootstrap and regress. OK for commit?
ChangeLog:
2021-06-01 Wilco Dijkstra <wdijk...@arm.com>
* config/aarch64/aarch64.cc (aarch64_rtx_costs): Use better
rematerialization
costs for HIGH, LO_SUM and SYMREF.
---
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index
43d87d1b9c4ef1a85094e51f81745f98f1ef27fb..7341849121ffd6b3b0b77c9730e74e751742e852
100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -14529,45 +14529,28 @@ cost_plus:
return false; /* All arguments need to be in registers. */
}
+ /* The following costs are used for rematerialization of addresses.
+ Set a low cost for all global accesses - this ensures they are
+ preferred for rematerialization, blocks them from being spilled
+ and reduces register pressure. The result is significant codesize
+ reductions and performance gains. */
+
case SYMBOL_REF:
+ *cost = 0;
- if (aarch64_cmodel == AARCH64_CMODEL_LARGE
- || aarch64_cmodel == AARCH64_CMODEL_SMALL_SPIC)
- {
- /* LDR. */
- if (speed)
- *cost += extra_cost->ldst.load;
- }
- else if (aarch64_cmodel == AARCH64_CMODEL_SMALL
- || aarch64_cmodel == AARCH64_CMODEL_SMALL_PIC)
- {
- /* ADRP, followed by ADD. */
- *cost += COSTS_N_INSNS (1);
- if (speed)
- *cost += 2 * extra_cost->alu.arith;
- }
- else if (aarch64_cmodel == AARCH64_CMODEL_TINY
- || aarch64_cmodel == AARCH64_CMODEL_TINY_PIC)
- {
- /* ADR. */
- if (speed)
- *cost += extra_cost->alu.arith;
- }
+ /* Use a separate remateralization cost for GOT accesses. */
+ if (aarch64_cmodel == AARCH64_CMODEL_SMALL_PIC
+ && aarch64_classify_symbol (x, 0) == SYMBOL_SMALL_GOT_4G)
+ *cost = COSTS_N_INSNS (1) / 2;
- if (flag_pic)
- {
- /* One extra load instruction, after accessing the GOT. */
- *cost += COSTS_N_INSNS (1);
- if (speed)
- *cost += extra_cost->ldst.load;
- }
return true;
case HIGH:
+ *cost = 0;
+ return true;
+
case LO_SUM:
- /* ADRP/ADD (immediate). */
- if (speed)
- *cost += extra_cost->alu.arith;
+ *cost = COSTS_N_INSNS (3) / 4;
return true;
case ZERO_EXTRACT:
