Hi,
this patch fixes ix86_adjust_cost for zen support. In particular the original
code was accounting memory latencies incorrectly (3 for integer, 2 for FP unit)
while they are 4 for integer and 7 for FP on this CPU.
Using lower latencies makes scheduler overly pesimistic about CPU's ability
to execute sequences involving loads effectively.
I have decided to split the code into new switch, even tought it is currently
similar to Athon-Buldozer tuning. The reason is that some extra special cases
will appear here and Zen is probably good place to cut away from sharing
implementation with older AMD designs.
Bootstrapped/regtested x86_64-linux, will commit it shortly.
* x86-tune-sched.c (ix86_adjust_cost): Fix Zen support.
Index: config/i386/x86-tune-sched.c
===================================================================
--- config/i386/x86-tune-sched.c (revision 253651)
+++ config/i386/x86-tune-sched.c (working copy)
@@ -352,7 +352,6 @@ ix86_adjust_cost (rtx_insn *insn, int de
case PROCESSOR_BDVER2:
case PROCESSOR_BDVER3:
case PROCESSOR_BDVER4:
- case PROCESSOR_ZNVER1:
case PROCESSOR_BTVER1:
case PROCESSOR_BTVER2:
case PROCESSOR_GENERIC:
@@ -387,6 +386,35 @@ ix86_adjust_cost (rtx_insn *insn, int de
if (cost >= loadcost)
cost -= loadcost;
+ else
+ cost = 0;
+ }
+ break;
+
+ case PROCESSOR_ZNVER1:
+ /* Stack engine allows to execute push&pop instructions in parall. */
+ if ((insn_type == TYPE_PUSH || insn_type == TYPE_POP)
+ && (dep_insn_type == TYPE_PUSH || dep_insn_type == TYPE_POP))
+ return 0;
+
+ memory = get_attr_memory (insn);
+
+ /* Show ability of reorder buffer to hide latency of load by executing
+ in parallel with previous instruction in case
+ previous instruction is not needed to compute the address. */
+ if ((memory == MEMORY_LOAD || memory == MEMORY_BOTH)
+ && !ix86_agi_dependent (dep_insn, insn))
+ {
+ enum attr_unit unit = get_attr_unit (insn);
+ int loadcost;
+
+ if (unit == UNIT_INTEGER || unit == UNIT_UNKNOWN)
+ loadcost = 4;
+ else
+ loadcost = 7;
+
+ if (cost >= loadcost)
+ cost -= loadcost;
else
cost = 0;
}
