- 01 Mar, 2021 9 commits
-
-
Manos Koukoutos authored
During loop exploration implemented for wasm loop unrolling, we can exit early if we already know that the loop is too large to unroll. Bug: v8:11298 Change-Id: I213edef995b58500d07d428f1f1a725132dd44e5 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2726501Reviewed-by:
Georg Neis <neis@chromium.org> Commit-Queue: Manos Koukoutos <manoskouk@chromium.org> Cr-Commit-Position: refs/heads/master@{#73095}
-
Mythri A authored
For adding stack checks in optimized code, we compute a conservative estimate of the frame size in the case of a deoptimization. Earlier we included the size of arguments adaptor frames used when actual arguments didn't match formal parameter count. Though we don't have an explicit adaptor frame, we should still include the size of these additional arguments when computing the frame size. Bug: chromium:1181240 Change-Id: Ib977c5492bb824762fe62aac5e4ffb1c2c233b86 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2723252Reviewed-by:
Jakob Gruber <jgruber@chromium.org> Reviewed-by:
Victor Gomes <victorgomes@chromium.org> Commit-Queue: Mythri Alle <mythria@chromium.org> Cr-Commit-Position: refs/heads/master@{#73094}
-
Toon Verwaest authored
Calls >4gb may have pretty bad performance on 64bit processors that use 32bits to encode branch prediction. By passing in a function in the binary as a hint to mmap it's more likely we'll be given an address close to the binary. This may significantly improve performance on many types of 64bit cores, especially those without hyperthreading. Change-Id: Ia1f712a3a029e10cb0c6a0d1e2c4919bbb2854f2 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2726500 Commit-Queue: Toon Verwaest <verwaest@chromium.org> Commit-Queue: Hannes Payer <hpayer@chromium.org> Auto-Submit: Toon Verwaest <verwaest@chromium.org> Reviewed-by:
Hannes Payer <hpayer@chromium.org> Cr-Commit-Position: refs/heads/master@{#73093}
-
Omer Katz authored
This CL sets it so that the actual object size is reported only when cppgc_enable_object_names is set to true. Otherwise the heap snapshot merges nodes and the sizes don't make sense. Also, this will resolve a web test failure for the library. Bug: chromium:1056170 Change-Id: I32f6552560bdfad4b64c67b21292543978042a81 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2726499Reviewed-by:
Michael Lippautz <mlippautz@chromium.org> Commit-Queue: Omer Katz <omerkatz@chromium.org> Cr-Commit-Position: refs/heads/master@{#73092}
-
Igor Sheludko authored
Bug: v8:11420,v8:11429 Change-Id: Ic08a1277b08a3de1ad1124dcedaeaf2fbd313c25 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2726495 Auto-Submit: Igor Sheludko <ishell@chromium.org> Commit-Queue: Leszek Swirski <leszeks@chromium.org> Reviewed-by:
Leszek Swirski <leszeks@chromium.org> Cr-Commit-Position: refs/heads/master@{#73091}
-
Camillo Bruni authored
Utils::ApiCheck has better usability and error messages in release mode. Bug: v8:11195 Change-Id: I80a31823df03b7581af2e6e8e4a52f6e39100c6a Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2721770Reviewed-by:
-
Dominik Inführ authored
To improve performance of parking, keep the thread state in an atomic variable instead of protecting it with a mutex. However the mutex was used e.g. to force Unpark() to block while the safepoint operation was still running. Therefore the safepoint algorithm has to change as well. Park() and Unpark() use CAS operation to transition the state. Safepoint() uses a relaxed load for checking whether a safepoint was requested. Since Safepoint(), Park() and Unpark() all have a slow path, there is no need for busy-waiting on the main thread. We need two more ThreadStates: * SafepointRequested: This state is set by GlobalSafepoint to force Running threads into the slow path on Safepoint() and Park(). This state also replaces the separate atomic<bool> safepoint_requested_ field we used before. * ParkedSafepoint: This state is set by GlobalSafepoint as well to force parked threads into the slow path on Unpark(). When stopping all threads, GlobalSafepoint transitions states from Running --> SafepointRequested and Parked --> ParkedSafepoint to force the slow path for all three methods. After performing the transition for each thread we know the exact number of Running threads and wait until each of them either reached a safepoint or parked itself. Design doc: https://docs.google.com/document/d/1p9klWyqT_AScAnK_PdHZTcNhZGzoBiYWPkUciIh2C58/edit?usp=sharing Bug: chromium:1177144, v8:10315 Change-Id: I8697da915c7d18e2fb941f1bedf6181226408feb Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2704075Reviewed-by:Ulan Degenbaev <ulan@chromium.org> Reviewed-by:
Maya Lekova <mslekova@chromium.org> Commit-Queue: Dominik Inführ <dinfuehr@chromium.org> Cr-Commit-Position: refs/heads/master@{#73089}
-
Liu Yu authored
Port: 679af80e Bug: v8:11377 Change-Id: I65902d260f72a33e816dfec6f6435e55d2fbd306 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2725673 Auto-Submit: Liu yu <liuyu@loongson.cn> Reviewed-by:
Zhao Jiazhong <zhaojiazhong-hf@loongson.cn> Commit-Queue: Zhao Jiazhong <zhaojiazhong-hf@loongson.cn> Cr-Commit-Position: refs/heads/master@{#73088}
-
v8-ci-autoroll-builder authored
Rolling v8/build: https://chromium.googlesource.com/chromium/src/build/+log/e28b4b7..06d89c7 Rolling v8/third_party/aemu-linux-x64: ftKmphEHEwMJc1_tTOsvx50Hd3J_GRNUTxp59ts3NjoC..12utHdzpAJMv14HvzgxQA19OLkI0UrGervsCs46ESbIC Rolling v8/third_party/catapult: https://chromium.googlesource.com/catapult/+log/6236096..df7850d Rolling v8/third_party/depot_tools: https://chromium.googlesource.com/chromium/tools/depot_tools/+log/8a2e6a7..e952fae TBR=v8-waterfall-sheriff@grotations.appspotmail.com Change-Id: Ia0bc8dfd0e53ae425022e383922fa9e56f11bf7a Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2726137Reviewed-by:
v8-ci-autoroll-builder <v8-ci-autoroll-builder@chops-service-accounts.iam.gserviceaccount.com> Commit-Queue: v8-ci-autoroll-builder <v8-ci-autoroll-builder@chops-service-accounts.iam.gserviceaccount.com> Cr-Commit-Position: refs/heads/master@{#73087}
-
- 28 Feb, 2021 1 commit
-
-
Paolo Severini authored
Fixes a problem with the inlining of JS-to-Wasm call wrappers into a surrounding exception handler and re-enables this case. Bug: v8:11092 Change-Id: I4937838c2b4a199e21f5ac90bee5b8e8de2470be Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2678341 Commit-Queue: Paolo Severini <paolosev@microsoft.com> Reviewed-by:
Clemens Backes <clemensb@chromium.org> Reviewed-by:
Andreas Haas <ahaas@chromium.org> Cr-Commit-Position: refs/heads/master@{#73086}
-
- 27 Feb, 2021 2 commits
-
-
Liu Yu authored
Port: 52cc7ba9 Bug: v8:11477 Change-Id: Ic4d518ae85b80077963b5034a3ac63c3bd2f152a Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2725672 Auto-Submit: Liu yu <liuyu@loongson.cn> Reviewed-by:
-
v8-ci-autoroll-builder authored
Rolling v8/build: https://chromium.googlesource.com/chromium/src/build/+log/be2a0bf..e28b4b7 Rolling v8/buildtools: https://chromium.googlesource.com/chromium/src/buildtools/+log/fd1ca3e..aa09fa7 Rolling v8/buildtools/third_party/libc++abi/trunk: https://chromium.googlesource.com/external/github.com/llvm/llvm-project/libcxxabi/+log/5fb4080..6918862 Rolling v8/third_party/aemu-linux-x64: 8c4TvsC0hrCVIdsAVOIoQ3TnOJ3PX5iVaUqg4iQkJP4C..ftKmphEHEwMJc1_tTOsvx50Hd3J_GRNUTxp59ts3NjoC Rolling v8/third_party/catapult: https://chromium.googlesource.com/catapult/+log/9105610..6236096 Rolling v8/third_party/depot_tools: https://chromium.googlesource.com/chromium/tools/depot_tools/+log/7d69005..8a2e6a7 TBR=v8-waterfall-sheriff@grotations.appspotmail.com Change-Id: If0bff6987bed992c9732c054200a4b5f41eddd1d Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2724864Reviewed-by:
-
- 26 Feb, 2021 19 commits
-
-
Deepti Gandluri authored
Change-Id: Id9b69f960887f55d26842ecad57c43367c7ddfcd Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2704951Reviewed-by:
Zhi An Ng <zhin@chromium.org> Commit-Queue: Deepti Gandluri <gdeepti@chromium.org> Cr-Commit-Position: refs/heads/master@{#73083}
-
Frank Tang authored
Add GetOptionsObject/CoerceOptionsToObject for ECMA402 2021 Change Intl.ListFormat / Intl.DisplayNames and Intl.Segmenter to use GetOptionsObject and keep old API under CoerceOptionsToObject based on https://github.com/tc39/ecma402/pull/538/files Test262 tests need to be changed per https://github.com/tc39/test262/issues/2950 Bug: v8:11466 Change-Id: I5cb9b7aba0556effc76b4005e95c90db1e59d41f Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2705696 Commit-Queue: Frank Tang <ftang@chromium.org> Reviewed-by:
Jakob Kummerow <jkummerow@chromium.org> Cr-Commit-Position: refs/heads/master@{#73082}
-
Michael Lippautz authored
This is a reland of eb453679 Original change's description: > cppgc: Rework testing GC infrastructure > > Instead of moving the stand-alone logic to the base heap, allows > specific heaps to override their stand-alone GC behavior. This allows > CppHeap to reuse the unified heap bottlenecks and visitors for > testing. This works as long as any v8 references are empty as there is > no Isolate attached to the heap in this case. > > - Reverts parts of https://crrev.com/c/2716291 > - Relands parts of https://crrev.com/c/2718146 > > In addition, add tests covering v8::CppHeap and cppgc::Heap. > > Bug: chromium:1056170 > Change-Id: I47dc88c7f0e4961a1aadd60da9b05bff4dcfb27a > Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718612 > Commit-Queue: Michael Lippautz <mlippautz@chromium.org> > Reviewed-by: Omer Katz <omerkatz@chromium.org> > Cr-Commit-Position: refs/heads/master@{#73077} Bug: chromium:1056170 Change-Id: I415c837a7cf275c636172485dc4101c237a7d76b Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2723253 Commit-Queue: Michael Lippautz <mlippautz@chromium.org> Commit-Queue: Omer Katz <omerkatz@chromium.org> Auto-Submit: Michael Lippautz <mlippautz@chromium.org> Reviewed-by:
Omer Katz <omerkatz@chromium.org> Cr-Commit-Position: refs/heads/master@{#73081}
-
Ng Zhi An authored
These were prototyped and not merged into the SIMD proposal. Bug: v8:10983 Change-Id: I5c30a0e9955ee5602e05d473f0f85be59d124205 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718761Reviewed-by:
Deepti Gandluri <gdeepti@chromium.org> Commit-Queue: Zhi An Ng <zhin@chromium.org> Cr-Commit-Position: refs/heads/master@{#73080}
-
Ng Zhi An authored
Optimize extadd_pairwise when AVX is supported. If SSE4_1 is available, we can use the SSE version of the same code sequence. However, there is a potentially better lowering that only requires SSE2, which has less instructions, but will only work better if we have rip-relative constants (otherwise even using ExternalReference it would be 2 moves). Bug: v8:11086,v8:11349 Change-Id: Iac6f31cf8052161846ff5242b4c18c638c83e0f6 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2719298Reviewed-by:
-
Francis McCabe authored
This reverts commit eb453679. Reason for revert: Breaks MSAN: https://ci.chromium.org/p/v8/builders/ci/V8%20Linux%20-%20arm64%20-%20sim%20-%20MSAN/37053 Original change's description: > cppgc: Rework testing GC infrastructure > > Instead of moving the stand-alone logic to the base heap, allows > specific heaps to override their stand-alone GC behavior. This allows > CppHeap to reuse the unified heap bottlenecks and visitors for > testing. This works as long as any v8 references are empty as there is > no Isolate attached to the heap in this case. > > - Reverts parts of https://crrev.com/c/2716291 > - Relands parts of https://crrev.com/c/2718146 > > In addition, add tests covering v8::CppHeap and cppgc::Heap. > > Bug: chromium:1056170 > Change-Id: I47dc88c7f0e4961a1aadd60da9b05bff4dcfb27a > Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718612 > Commit-Queue: Michael Lippautz <mlippautz@chromium.org> > Reviewed-by: Omer Katz <omerkatz@chromium.org> > Cr-Commit-Position: refs/heads/master@{#73077} Bug: chromium:1056170 Change-Id: Ieda44c07d08f837a6632f96b8db6d5bec87dd521 No-Presubmit: true No-Tree-Checks: true No-Try: true Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2723216 Bot-Commit: Rubber Stamper <rubber-stamper@appspot.gserviceaccount.com> Commit-Queue: Francis McCabe <fgm@chromium.org> Cr-Commit-Position: refs/heads/master@{#73078}
-
Michael Lippautz authored
Instead of moving the stand-alone logic to the base heap, allows specific heaps to override their stand-alone GC behavior. This allows CppHeap to reuse the unified heap bottlenecks and visitors for testing. This works as long as any v8 references are empty as there is no Isolate attached to the heap in this case. - Reverts parts of https://crrev.com/c/2716291 - Relands parts of https://crrev.com/c/2718146 In addition, add tests covering v8::CppHeap and cppgc::Heap. Bug: chromium:1056170 Change-Id: I47dc88c7f0e4961a1aadd60da9b05bff4dcfb27a Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718612 Commit-Queue: Michael Lippautz <mlippautz@chromium.org> Reviewed-by:
-
Milad Fa authored
Port 52cc7ba9 Original Commit Message: This renames more fields holding "ValueKind" or methods operating on "ValueKind" to contain "kind" instead of "type". It also renames "is_reference_type" to "is_reference" on both ValueType and ValueKind, as the "_type" prefix is kind of implicit from the argument. R=clemensb@chromium.org, joransiu@ca.ibm.com, junyan@redhat.com, midawson@redhat.com BUG= LOG=N Change-Id: I3ab73b31b401ed1e9788df33d998b067280cb52c Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2723251Reviewed-by:
-
Ng Zhi An authored
Drive-by cleanups to merge macro lists which now have the same instruction selector requirements. Bug: v8:11384 Change-Id: Id49c43dce897685d5ced19509f390274805739aa Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2716069Reviewed-by:
-
Santiago Aboy Solanes authored
Bug: v8:7790 Change-Id: I8ff80b109381b339864879e8e4e0dc0d5e418262 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2682636Reviewed-by:
-
pthier authored
Using an out-parameter for the SFI data type in GetSharedFunctionInfoCode() avoids loading the CodeKind in CompileLazy(). Bug: v8:11429 Change-Id: Ib8eccdf6d169cce28a9ff50bb415447b61ad71a9 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2715197 Auto-Submit: Patrick Thier <pthier@chromium.org> Reviewed-by:
-
Manos Koukoutos authored
We experimentally globally enable loop unrolling for wasm code. This might be reverted based on the results of perf bots. Additional change: Add LoopExitValue to Int64Lowering, plus a small simplification. Bug: v8:11298 Change-Id: Iaf2829e80f948d70c5fb6ed7c974db7f59265fa3 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718611Reviewed-by:
-
Clemens Backes authored
Wasm tests and wasm fuzzers should not be compiled (and run) if v8_enable_webassembly=false. R=machenbach@chromium.org Bug: v8:11238 Change-Id: I78bbb1d1d98179cac315411b8c2c2ecaee8ede91 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2721761Reviewed-by:
Michael Achenbach <machenbach@chromium.org> Commit-Queue: Clemens Backes <clemensb@chromium.org> Cr-Commit-Position: refs/heads/master@{#73071}
-
Clemens Backes authored
This renames more fields holding "ValueKind" or methods operating on "ValueKind" to contain "kind" instead of "type". It also renames "is_reference_type" to "is_reference" on both ValueType and ValueKind, as the "_type" prefix is kind of implicit from the argument. R=manoskouk@chromium.org, jgruber@chromium.org Bug: v8:11477 Change-Id: I7809f1af6e983aebca96e03fe1fbc6ccaa22db72 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2718063 Commit-Queue: Clemens Backes <clemensb@chromium.org> Reviewed-by:
Manos Koukoutos <manoskouk@chromium.org> Reviewed-by:
-
Liu Yu authored
Port: 47ffa7a5 Bug: v8:6020 Change-Id: I4ae6261828b27f88553781a93d8557b6b685c217 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2719811 Auto-Submit: Liu yu <liuyu@loongson.cn> Reviewed-by:
-
Clemens Backes authored
In https://crrev.com/c/2707170, Liftoff was changed to only store the ValueKind instead of the ValueType, because we only need to know kind for code emission. For debugging though, the whole type is useful. This CL changes the debug sidetable back to store the full type, and retrieves this information from the decoder. R=jkummerow@chromium.org Bug: v8:11477 Change-Id: I08a512d24cdf0955c95f3b9261d68a02a39b9b4e Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720302 Commit-Queue: Clemens Backes <clemensb@chromium.org> Reviewed-by:
-
LiuYu authored
Simd unsupported in simulator and some machines on mips. Original Commit Message: As of https://crrev.com/c/2629465, Simd tests cannot pass on architectures without Simd support. Tests will need to be re-enabled once Simd support is fully implemented on PPC. Port: aaacffa1 Change-Id: Ic7451211cbe2bfa13952b994ea440189620579cd Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2717158 Auto-Submit: Liu yu <liuyu@loongson.cn> Reviewed-by:
-
v8-ci-autoroll-builder authored
Rolling v8/build: https://chromium.googlesource.com/chromium/src/build/+log/67d73b8..be2a0bf Rolling v8/buildtools: https://chromium.googlesource.com/chromium/src/buildtools/+log/45fb4c0..fd1ca3e Rolling v8/third_party/aemu-linux-x64: qI8e328VwkWv64EapCvG3Xj9_hDpKQFuJWeVdUHz7W0C..8c4TvsC0hrCVIdsAVOIoQ3TnOJ3PX5iVaUqg4iQkJP4C Rolling v8/third_party/catapult: https://chromium.googlesource.com/catapult/+log/a34cee3..9105610 Rolling v8/third_party/depot_tools: https://chromium.googlesource.com/chromium/tools/depot_tools/+log/fb09de2..7d69005 Rolling v8/tools/clang: https://chromium.googlesource.com/chromium/src/tools/clang/+log/823927c..6a9fd91 TBR=v8-waterfall-sheriff@grotations.appspotmail.com Change-Id: I013a44bd204f5acb8a0af9ec71b7f29945e9dbd1 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2721362Reviewed-by:
-
Omer Katz authored
This was causing DevTools to crush whenever I took a heap snapshot. Bug: chromium:1056170 Change-Id: Ice7b3039c21a3f902f242299939e92ba0e393c9f Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720307 Commit-Queue: Omer Katz <omerkatz@chromium.org> Reviewed-by:
-
- 25 Feb, 2021 9 commits
-
-
Omer Katz authored
This CL adds WasConservativeGC to HeapState which reports whether the last GC was finalized conservatively. The state is updated at the end of marking atomic pause. Currently the library integration in Blink ignores the stack state when scheduling a forced GC for testing. That means that we always schedule another GC after a forced GC. This causes a crash in web_tests which assume no GC is happening between forced GCs if the thread is not idle and no new allocations happen. Usage CL: https://crrev.com/c/2720201 Drive by: Fix stack state for MarkingVerifier in CppHeap. Bug: chromium:1056170 Change-Id: I6ad23ed7c1a53fae96425b968bc4b3eb18ce80b7 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720279 Commit-Queue: Omer Katz <omerkatz@chromium.org> Reviewed-by:
-
Ng Zhi An authored
Bug: v8:11347 Change-Id: I17859b226e14df63380dd6895bee62b0e8a380b9 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2719297Reviewed-by:
-
Milad Fa authored
Change-Id: I49d0911fe72f624cd0700e6aafaadb9fdc401f93 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720466Reviewed-by:
Junliang Yan <junyan@redhat.com> Commit-Queue: Milad Fa <mfarazma@redhat.com> Cr-Commit-Position: refs/heads/master@{#73062}
-
Milad Fa authored
Port 47ffa7a5 Original Commit Message: This instruction is not in the final SIMD proposal. R=zhin@chromium.org, joransiu@ca.ibm.com, junyan@redhat.com, midawson@redhat.com BUG= LOG=N Change-Id: I7e701fb6a995fb62737e9473cdf76a33c5518cac Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2716055Reviewed-by:
-
Michael Lippautz authored
- cppgc_headers: Do not depend on any internals but merely expose the public API interface. - v8_libbase: Do not depend on v8_headers but merely on v8_config_headers as src/base should be independent of general V8. Bug: chromium:1056170 Change-Id: I06d1a4ea20f243bae8e994deba9d76f07993ed4a Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720303Reviewed-by:
Dan Elphick <delphick@chromium.org> Commit-Queue: Michael Lippautz <mlippautz@chromium.org> Cr-Commit-Position: refs/heads/master@{#73060}
-
Milad Fa authored
This CL also adds and makes use of the __int128 data type to help with vector loads and stores. Change-Id: I0d02eddcedfe17d12eadd214e205b693fa7ebe53 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2720459Reviewed-by:
-
Ng Zhi An authored
This instruction is not in the final SIMD proposal. Bug: v8:6020 Change-Id: Ifef1b3d58bf660f2d30784f587aed85f327825ec Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2716073 Commit-Queue: Zhi An Ng <zhin@chromium.org> Reviewed-by:
-
Ng Zhi An authored
Improve SSE codegen similar to suggestions in https://crrev.com/c/2698066: - s/movdqa/movaps/ - s/por/orps - s/pxor/xorps - s/pand/andps - use movshdup (SSSE3) insted of shuffle Bug: v8:11415 Change-Id: I2e76cbbe16267c055e24f258354b77994aed47b8 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2713131Reviewed-by:
-
Ng Zhi An authored
Copy paste error leading to wrong definition. Change-Id: I93c516d11ed4c76ed389afb6e911315a8ce49ef0 Reviewed-on: https://chromium-review.googlesource.com/c/v8/v8/+/2716741 Commit-Queue: Zhi An Ng <zhin@chromium.org> Reviewed-by:
-
