source: webkit/trunk/LayoutTests/workers/sab/worker-resources.js @ 221337

Last change on this file since 221337 was 215565, checked in by fpizlo@apple.com, 7 years ago

Optimize SharedArrayBuffer in the DFG+FTL
​https://bugs.webkit.org/show_bug.cgi?id=164108

Reviewed by Saam Barati.

JSTests:

Added a fairly comprehensive test of the intrinsics. This creates a function for each possible
combination of type and operation, and then first uses it nicely and then tries a bunch of
erroneous conditions like OOB.

  • stress/SharedArrayBuffer-opt.js: Added.

(string_appeared_here.switch):
(string_appeared_here.str):
(runAtomic):
(shouldFail):
(Symbol):
(string_appeared_here.a.of.arrays.m.of.atomics):

  • stress/SharedArrayBuffer.js:

Source/JavaScriptCore:

This adds atomics intrinsics to the DFG and wires them through to the DFG and FTL backends. This
was super easy in the FTL since B3 already has comprehensive atomic intrinsics, which are more
powerful than what we need right now. In the DFG backend, I went with an easy-to-write
implementation that just reduces everything to a weak CAS loop. It's very inefficient with
registers (it needs ~8) but it's the DFG backend, so it's not obvious how much we care.

To make the rare cases easy to handle, I refactored AtomicsObject.cpp so that the operations for
the slow paths can share code with the native functions.

This also fixes register handling in the X86 implementations of CAS, in the case that
expectedAndResult is not %rax. This also fixes the ARM64 implementation of branchWeakCAS.

I adapted the CascadeLock from WTF/benchmarks/ToyLocks.h as a microbenchmark of lock performance.
This benchmark performs 2.5x faster, in both the contended and uncontended case, thanks to this
change. It's still about 3x slower than native. I investigated this only a bit. I suspect that
the story will be different in asm.js code, which will get constant-folding of the typed array
backing store by virtue of how it uses lexically scoped variables as pointers to the heap arrays.
It's worth noting that the native lock I was comparing against, the very nicely-tuned
CascadeLock, is at the very high end of lock throughput under virtually all conditions
(uncontended, microcontended, held for a long time). I also compared to WTF::Lock and others, and
the only ones that performed better in this microbenchmark were spinlocks. I don't recommend
using those. So, when I say this is 3x slower than native, I really mean that it's 3x slower than
the fastest native lock that I have in my arsenal.

Also worth noting is that I experimented with exposing Atomics.yield(), which uses sched_yield,
as a way of testing if adding a yield loop to the JS cascadeLock would help. It does not help. I
did not investigate why.

  • assembler/AbstractMacroAssembler.h:

(JSC::AbstractMacroAssembler::JumpList::append):

  • assembler/CPU.h:

(JSC::is64Bit):
(JSC::is32Bit):

  • b3/B3Common.h:

(JSC::B3::is64Bit): Deleted.
(JSC::B3::is32Bit): Deleted.

  • b3/B3LowerToAir.cpp:

(JSC::B3::Air::LowerToAir::appendTrapping):
(JSC::B3::Air::LowerToAir::appendCAS):
(JSC::B3::Air::LowerToAir::appendGeneralAtomic):

  • dfg/DFGAbstractInterpreterInlines.h:

(JSC::DFG::AbstractInterpreter<AbstractStateType>::executeEffects):

  • dfg/DFGByteCodeParser.cpp:

(JSC::DFG::ByteCodeParser::handleIntrinsicCall):

  • dfg/DFGClobberize.h:

(JSC::DFG::clobberize):

  • dfg/DFGDoesGC.cpp:

(JSC::DFG::doesGC):

  • dfg/DFGFixupPhase.cpp:

(JSC::DFG::FixupPhase::fixupNode):

  • dfg/DFGNode.h:

(JSC::DFG::Node::hasHeapPrediction):
(JSC::DFG::Node::hasArrayMode):

  • dfg/DFGNodeType.h:

(JSC::DFG::isAtomicsIntrinsic):
(JSC::DFG::numExtraAtomicsArgs):

  • dfg/DFGPredictionPropagationPhase.cpp:
  • dfg/DFGSSALoweringPhase.cpp:

(JSC::DFG::SSALoweringPhase::handleNode):

  • dfg/DFGSafeToExecute.h:

(JSC::DFG::safeToExecute):

  • dfg/DFGSpeculativeJIT.cpp:

(JSC::DFG::SpeculativeJIT::loadFromIntTypedArray):
(JSC::DFG::SpeculativeJIT::setIntTypedArrayLoadResult):
(JSC::DFG::SpeculativeJIT::compileGetByValOnIntTypedArray):
(JSC::DFG::SpeculativeJIT::getIntTypedArrayStoreOperand):
(JSC::DFG::SpeculativeJIT::compilePutByValForIntTypedArray):

  • dfg/DFGSpeculativeJIT.h:

(JSC::DFG::SpeculativeJIT::callOperation):

  • dfg/DFGSpeculativeJIT32_64.cpp:

(JSC::DFG::SpeculativeJIT::compile):

  • dfg/DFGSpeculativeJIT64.cpp:

(JSC::DFG::SpeculativeJIT::compile):

  • ftl/FTLAbstractHeapRepository.cpp:

(JSC::FTL::AbstractHeapRepository::decorateFencedAccess):
(JSC::FTL::AbstractHeapRepository::computeRangesAndDecorateInstructions):

  • ftl/FTLAbstractHeapRepository.h:
  • ftl/FTLCapabilities.cpp:

(JSC::FTL::canCompile):

  • ftl/FTLLowerDFGToB3.cpp:

(JSC::FTL::DFG::LowerDFGToB3::compileNode):
(JSC::FTL::DFG::LowerDFGToB3::compileAtomicsReadModifyWrite):
(JSC::FTL::DFG::LowerDFGToB3::compileAtomicsIsLockFree):
(JSC::FTL::DFG::LowerDFGToB3::compileGetByVal):
(JSC::FTL::DFG::LowerDFGToB3::compilePutByVal):
(JSC::FTL::DFG::LowerDFGToB3::pointerIntoTypedArray):
(JSC::FTL::DFG::LowerDFGToB3::loadFromIntTypedArray):
(JSC::FTL::DFG::LowerDFGToB3::storeType):
(JSC::FTL::DFG::LowerDFGToB3::setIntTypedArrayLoadResult):
(JSC::FTL::DFG::LowerDFGToB3::getIntTypedArrayStoreOperand):
(JSC::FTL::DFG::LowerDFGToB3::vmCall):

  • ftl/FTLOutput.cpp:

(JSC::FTL::Output::store):
(JSC::FTL::Output::store32As8):
(JSC::FTL::Output::store32As16):
(JSC::FTL::Output::atomicXchgAdd):
(JSC::FTL::Output::atomicXchgAnd):
(JSC::FTL::Output::atomicXchgOr):
(JSC::FTL::Output::atomicXchgSub):
(JSC::FTL::Output::atomicXchgXor):
(JSC::FTL::Output::atomicXchg):
(JSC::FTL::Output::atomicStrongCAS):

  • ftl/FTLOutput.h:

(JSC::FTL::Output::store32):
(JSC::FTL::Output::store64):
(JSC::FTL::Output::storePtr):
(JSC::FTL::Output::storeFloat):
(JSC::FTL::Output::storeDouble):

  • jit/JITOperations.h:
  • runtime/AtomicsObject.cpp:

(JSC::atomicsFuncAdd):
(JSC::atomicsFuncAnd):
(JSC::atomicsFuncCompareExchange):
(JSC::atomicsFuncExchange):
(JSC::atomicsFuncIsLockFree):
(JSC::atomicsFuncLoad):
(JSC::atomicsFuncOr):
(JSC::atomicsFuncStore):
(JSC::atomicsFuncSub):
(JSC::atomicsFuncWait):
(JSC::atomicsFuncWake):
(JSC::atomicsFuncXor):
(JSC::operationAtomicsAdd):
(JSC::operationAtomicsAnd):
(JSC::operationAtomicsCompareExchange):
(JSC::operationAtomicsExchange):
(JSC::operationAtomicsIsLockFree):
(JSC::operationAtomicsLoad):
(JSC::operationAtomicsOr):
(JSC::operationAtomicsStore):
(JSC::operationAtomicsSub):
(JSC::operationAtomicsXor):

  • runtime/AtomicsObject.h:

Source/WTF:

Made small changes as part of benchmarking the JS versions of these locks.

  • benchmarks/LockSpeedTest.cpp:
  • benchmarks/ToyLocks.h:
  • wtf/Range.h:

(WTF::Range::dump):

LayoutTests:

Add a test of futex performance.

  • workers/sab/cascade_lock-worker.js: Added.

(onmessage):

  • workers/sab/cascade_lock.html: Added.
  • workers/sab/worker-resources.js:

(cascadeLockSlow):
(cascadeLock):
(cascadeUnlock):
File size: 2.5 KB
Line 
1function wait(memory, index, waitCondition, wakeCondition)
2{
3    while (memory[index] == waitCondition) {
4        var result = Atomics.wait(memory, index, waitCondition);
5        switch (result) {
6        case "not-equal":
7        case "ok":
8            break;
9        default:
10            postMessage("Error: bad result from wait: " + result);
11            postMessage("error");
12            break;
13        }
14        var value = memory[index];
15        if (value != wakeCondition) {
16            postMessage("Error: wait returned not-equal but the memory has a bad value: " + value);
17            postMessage("error");
18        }
19    }
20    var value = memory[index];
21    if (value != wakeCondition) {
22        postMessage("Error: done waiting but the memory has a bad value: " + value);
23        postMessage("error");
24    }
25}
26
27function wake(memory, index)
28{
29    var result = Atomics.wake(memory, index, 1);
30    if (result != 0 && result != 1) {
31        postMessage("Error: bad result from wake: " + result);
32        postMessage("error");
33    }
34}
35
36function checkBufferSharing(shouldShareBuffer)
37{
38    var set = new Set();
39    for (var i = 1; i < arguments.length; ++i)
40        set.add(arguments[i].buffer);
41    if (shouldShareBuffer) {
42        if (set.size != 1) {
43            postMessage("Error: buffers should be shared but are not shared (set.size == " + set.size + ")");
44            postMessage("error");
45        }
46    } else {
47        if (set.size != arguments.length - 1) {
48            postMessage("Error: buffers should not be shared but are shared");
49            postMessage("error");
50        }
51    }
52}
53
54var cascadeLockUnlocked = 0;
55var cascadeLockLocked = 1;
56var cascadeLockLockedAndParked = 2;
57
58function cascadeLockSlow(memory, index)
59{
60    var desiredState = cascadeLockLocked;
61    for (;;) {
62        if (Atomics.compareExchange(memory, index, cascadeLockUnlocked, desiredState) == cascadeLockUnlocked)
63            return;
64       
65        desiredState = cascadeLockLockedAndParked;
66        Atomics.compareExchange(memory, index, cascadeLockLocked, cascadeLockLockedAndParked);
67        Atomics.wait(memory, index, cascadeLockLockedAndParked);
68    }
69}
70
71function cascadeLock(memory, index)
72{
73    if (Atomics.compareExchange(memory, index, cascadeLockUnlocked, cascadeLockLocked) == cascadeLockUnlocked)
74        return;
75   
76    cascadeLockSlow(memory, index);
77}
78
79function cascadeUnlock(memory, index)
80{
81    if (Atomics.exchange(memory, index, cascadeLockUnlocked) == cascadeLockLocked)
82        return;
83
84    Atomics.wake(memory, index, 1);
85}
86
Note: See TracBrowser for help on using the repository browser.