Add an optimization for removing redundant suspend tests in ART
This CL:
(1) eliminates redundant suspend checks (dominated by another check),
(2) removes the special treatment of the R4 register, which got
reset on every native call, possibly yielding long execution
sequences without any suspend checks, and
(3) fixes the absence of suspend checks in leaf methods.
(2) and (3) increase the frequency of suspend checks, which improves
the performance of GC and the accuracy of profile data. To
compensate for the increased number of checks, we implemented an
optimization that leverages dominance information to remove
redundant suspend checks on back edges. Based on the results of
running the Caffeine benchmark on Nexus 7, the patch performs
roughly 30% more useful suspend checks, spreading them much more
evenly along the execution trace, while incurring less than 1%
overhead. For flexibility consideration, this CL defines two flags
to control the enabling of optimizations. The original
implementation is the default.
Change-Id: I31e81a5b3c53030444dbe0434157274c9ab8640f
Signed-off-by: Wei Jin <wejin@google.com>
diff --git a/runtime/arch/arm/quick_entrypoints_arm.S b/runtime/arch/arm/quick_entrypoints_arm.S
index 5212576..83a683d 100644
--- a/runtime/arch/arm/quick_entrypoints_arm.S
+++ b/runtime/arch/arm/quick_entrypoints_arm.S
@@ -330,7 +330,9 @@
mov r11, sp @ save the stack pointer
.cfi_def_cfa_register r11
mov r9, r3 @ move managed thread pointer into r9
+#ifdef ARM_R4_SUSPEND_FLAG
mov r4, #SUSPEND_CHECK_INTERVAL @ reset r4 to suspend check interval
+#endif
add r5, r2, #16 @ create space for method pointer in frame
and r5, #0xFFFFFFF0 @ align frame size to 16 bytes
sub sp, r5 @ reserve stack space for argument array
@@ -932,11 +934,13 @@
*/
.extern artTestSuspendFromCode
ENTRY art_quick_test_suspend
+#ifdef ARM_R4_SUSPEND_FLAG
ldrh r0, [rSELF, #THREAD_FLAGS_OFFSET]
mov rSUSPEND, #SUSPEND_CHECK_INTERVAL @ reset rSUSPEND to SUSPEND_CHECK_INTERVAL
cbnz r0, 1f @ check Thread::Current()->suspend_count_ == 0
bx lr @ return if suspend_count_ == 0
1:
+#endif
mov r0, rSELF
SETUP_REF_ONLY_CALLEE_SAVE_FRAME @ save callee saves for stack crawl
mov r1, sp