Use iterators "before" the use node in HUserRecord<>.
Create a new template class IntrusiveForwardList<> that
mimicks std::forward_list<> except that all allocations
are handled externally. This is essentially the same as
boost::intrusive::slist<> but since we're not using Boost
we have to reinvent the wheel.
Use the new container to replace the HUseList and use the
iterators to "before" use nodes in HUserRecord<> to avoid
the extra pointer to the previous node which was used
exclusively for removing nodes from the list. This reduces
the size of the HUseListNode by 25%, 32B to 24B in 64-bit
compiler, 16B to 12B in 32-bit compiler. This translates
directly to overall memory savings for the 64-bit compiler
but due to rounding up of the arena allocations to 8B, we
do not get any improvement in the 32-bit compiler.
Compiling the Nexus 5 boot image with the 64-bit dex2oat
on host this CL reduces the memory used for compiling the
most hungry method, BatteryStats.dumpLocked(), by ~3.3MiB:
Before:
MEM: used: 47829200, allocated: 48769120, lost: 939920
Number of arenas allocated: 345,
Number of allocations: 815492, avg size: 58
...
UseListNode 13744640
...
After:
MEM: used: 44393040, allocated: 45361248, lost: 968208
Number of arenas allocated: 319,
Number of allocations: 815492, avg size: 54
...
UseListNode 10308480
...
Note that while we do not ship the 64-bit dex2oat to the
device, the JIT compilation for 64-bit processes is using
the 64-bit libart-compiler.
Bug: 28173563
Change-Id: I985eabd4816f845372d8aaa825a1489cf9569208
diff --git a/compiler/optimizing/instruction_simplifier_arm64.cc b/compiler/optimizing/instruction_simplifier_arm64.cc
index f00d960..e4a711e 100644
--- a/compiler/optimizing/instruction_simplifier_arm64.cc
+++ b/compiler/optimizing/instruction_simplifier_arm64.cc
@@ -140,7 +140,7 @@
shift_amount,
use->GetDexPc());
use->GetBlock()->ReplaceAndRemoveInstructionWith(use, alu_with_op);
- if (bitfield_op->GetUses().IsEmpty()) {
+ if (bitfield_op->GetUses().empty()) {
bitfield_op->GetBlock()->RemoveInstruction(bitfield_op);
}
RecordSimplification();
@@ -160,20 +160,22 @@
const HUseList<HInstruction*>& uses = bitfield_op->GetUses();
// Check whether we can merge the instruction in all its users' shifter operand.
- for (HUseIterator<HInstruction*> it_use(uses); !it_use.Done(); it_use.Advance()) {
- HInstruction* use = it_use.Current()->GetUser();
- if (!HasShifterOperand(use)) {
+ for (const HUseListNode<HInstruction*>& use : uses) {
+ HInstruction* user = use.GetUser();
+ if (!HasShifterOperand(user)) {
return false;
}
- if (!CanMergeIntoShifterOperand(use, bitfield_op)) {
+ if (!CanMergeIntoShifterOperand(user, bitfield_op)) {
return false;
}
}
// Merge the instruction into its uses.
- for (HUseIterator<HInstruction*> it_use(uses); !it_use.Done(); it_use.Advance()) {
- HInstruction* use = it_use.Current()->GetUser();
- bool merged = MergeIntoShifterOperand(use, bitfield_op);
+ for (auto it = uses.begin(), end = uses.end(); it != end; /* ++it below */) {
+ HInstruction* user = it->GetUser();
+ // Increment `it` now because `*it` will disappear thanks to MergeIntoShifterOperand().
+ ++it;
+ bool merged = MergeIntoShifterOperand(user, bitfield_op);
DCHECK(merged);
}