Page MenuHomePhabricator

pengfei (Pengfei Wang)
User

Projects

User does not belong to any projects.

User Details

User Since
Dec 12 2018, 5:57 PM (68 w, 5 d)

Recent Activity

Sun, Mar 29

pengfei added a comment to D76190: CET for Exception Handle.

@pengfei You can strip unneeded Phabricator tags with:

% which arcfilter
arcfilter () {
        git log -1 --pretty=%B | awk '/Reviewers:|Subscribers:/{p=1} /Reviewed By:|Differential Revision:/{p=0} !p && !/^Summary:$/ {sub(/^Summary: /,
"");print}' | git commit --amend -F -
}

Subscribers: and Reviewers: are just annoying. It is also not appropriate to use Patch By: Xiang Zhang (xiangzhangllvm). See https://llvm.org/docs/DeveloperPolicy.html#commit-messages " git commit --amend --author="John Doe <jdoe@llvm.org> to correct the author property"

Sun, Mar 29, 6:12 PM · Restricted Project

Tue, Mar 17

pengfei committed rG974d649f8eaf: CET for Exception Handle (authored by pengfei).
CET for Exception Handle
Tue, Mar 17, 10:41 PM
pengfei closed D76190: CET for Exception Handle.
Tue, Mar 17, 10:41 PM · Restricted Project

Mar 3 2020

pengfei added a comment to D75506: [X86] Fix bug: Scalar FMA intrinsics generate wrong result.

Doesn't the modifier {z} clean the upper 64 bits?

Mar 3 2020, 2:09 AM · Restricted Project

Feb 26 2020

pengfei added inline comments to D75224: [SelectionDAG][FPEnv] Take into account SelectionDAG continuous CSE when setting the nofpexcept flag for constrained intrinsics.
Feb 26 2020, 8:04 PM · Restricted Project

Feb 13 2020

pengfei accepted D74552: [X86] Fix bug that mm_mask_cvtsepi64_epi32 generates result without zero the upper 64bit.

LGTM.

Feb 13 2020, 7:30 AM · Restricted Project

Feb 3 2020

pengfei accepted D73864: [X86] FUCOMI/FCOMI instructions should Def FPSW not FPCW..

Agreed, LGTM.

Feb 3 2020, 3:34 AM · Restricted Project

Jan 31 2020

pengfei added inline comments to D73784: [FPEnv][AArch64] Add lowering of f128 STRICT_FSETCC.
Jan 31 2020, 7:12 AM · Restricted Project
pengfei added inline comments to D73784: [FPEnv][AArch64] Add lowering of f128 STRICT_FSETCC.
Jan 31 2020, 6:33 AM · Restricted Project

Jan 29 2020

pengfei added inline comments to D73625: [FPEnv][AArch64] Add lowering and instruction selection for strict conversions.
Jan 29 2020, 6:30 PM · Restricted Project

Jan 28 2020

pengfei committed rGdba8cd5438c3: Fix sphinx build bot failure. NFCI. (authored by pengfei).
Fix sphinx build bot failure. NFCI.
Jan 28 2020, 6:13 AM
pengfei added inline comments to D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 28 2020, 6:04 AM · Restricted Project, Restricted Project
pengfei committed rG3239b5034ee9: [FPEnv] Add pragma FP_CONTRACT support under strict FP. (authored by pengfei).
[FPEnv] Add pragma FP_CONTRACT support under strict FP.
Jan 28 2020, 4:50 AM
pengfei closed D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 28 2020, 4:50 AM · Restricted Project, Restricted Project
pengfei committed rG3d1f0ce3b9f8: [X86] Add combination for fma and fneg on X86 under strict FP. (authored by pengfei).
[X86] Add combination for fma and fneg on X86 under strict FP.
Jan 28 2020, 4:32 AM
pengfei closed D72824: [X86] Add combination for fma and fneg on X86 under strict FP..
Jan 28 2020, 4:32 AM · Restricted Project

Jan 26 2020

pengfei added inline comments to D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 26 2020, 9:19 PM · Restricted Project, Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Address review comment.

Jan 26 2020, 9:19 PM · Restricted Project, Restricted Project
pengfei updated the diff for D72824: [X86] Add combination for fma and fneg on X86 under strict FP..

Rebase and add vector instructions test.

Jan 26 2020, 8:10 PM · Restricted Project
pengfei committed rG17b8f96d65e4: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and… (authored by pengfei).
[FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and…
Jan 26 2020, 6:56 PM
pengfei closed D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI..
Jan 26 2020, 6:56 PM · Restricted Project

Jan 23 2020

pengfei added a comment to D72824: [X86] Add combination for fma and fneg on X86 under strict FP..

Add to isNegatibleForFree/getNegatedExpression as well?

Jan 23 2020, 1:25 AM · Restricted Project

Jan 17 2020

pengfei added a child revision for D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI.: D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 17 2020, 7:18 AM · Restricted Project
pengfei added a parent revision for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP.: D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI..
Jan 17 2020, 7:18 AM · Restricted Project, Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Remove unnecessary comment.

Jan 17 2020, 7:09 AM · Restricted Project, Restricted Project
pengfei added inline comments to D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 17 2020, 7:09 AM · Restricted Project, Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Address review comments.

Jan 17 2020, 6:59 AM · Restricted Project, Restricted Project

Jan 16 2020

pengfei retitled D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI. from [FPEnv] Alternative implementation of constrained fmuladd that avoids fmuladd ISD opcodes to [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI..
Jan 16 2020, 6:53 PM · Restricted Project
pengfei updated the diff for D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI..

Removed the FP_CONTRACT support code.

Jan 16 2020, 6:53 PM · Restricted Project
pengfei commandeered D72871: [FPEnv] Divide macro INSTRUCTION into INSTRUCTION and DAG_INSTRUCTION, and macro FUNCTION likewise. NFCI..
Jan 16 2020, 6:43 PM · Restricted Project
pengfei updated the diff for D72824: [X86] Add combination for fma and fneg on X86 under strict FP..

Add FMA4 tests. Thanks @RKSimon.

Jan 16 2020, 12:44 AM · Restricted Project

Jan 15 2020

pengfei retitled D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP. from Add pragma FP_CONTRACT support. to [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 15 2020, 10:09 PM · Restricted Project, Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Address review comment.

Jan 15 2020, 10:05 PM · Restricted Project, Restricted Project
pengfei created D72824: [X86] Add combination for fma and fneg on X86 under strict FP..
Jan 15 2020, 9:56 PM · Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Address review comments.

Jan 15 2020, 9:10 PM · Restricted Project, Restricted Project
pengfei updated the diff for D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..

Remove dead code.

Jan 15 2020, 7:29 PM · Restricted Project, Restricted Project
pengfei created D72820: [FPEnv] Add pragma FP_CONTRACT support under strict FP..
Jan 15 2020, 7:11 PM · Restricted Project, Restricted Project

Jan 13 2020

pengfei added a comment to D72665: [X86] Break the loop in LowerReturn into 2 loops..

Yeah, it's useful and clear to use a STRICT_FP_EXTEND. Anyway, I think we can also achieve it by getting the function's attribute or propagating the fpexcept to FP_EXTEND.

Jan 13 2020, 7:18 PM · Restricted Project
pengfei added a comment to D72665: [X86] Break the loop in LowerReturn into 2 loops..

Do we really need to distinguish STRICT_FP_EXTEND and FP_EXTEND for a return? Currently the STRICT nodes are used to avoid to be optimized out or reordered. But I think neither occurs for a return.

Jan 13 2020, 6:41 PM · Restricted Project

Jan 10 2020

pengfei added inline comments to D72466: [FPEnv][RFC] Invert sense of MIFlag::FPExcept flag.
Jan 10 2020, 12:00 AM · Restricted Project

Jan 9 2020

pengfei added inline comments to D72466: [FPEnv][RFC] Invert sense of MIFlag::FPExcept flag.
Jan 9 2020, 10:25 PM · Restricted Project
pengfei added inline comments to D72466: [FPEnv][RFC] Invert sense of MIFlag::FPExcept flag.
Jan 9 2020, 6:49 PM · Restricted Project
pengfei added inline comments to D72466: [FPEnv][RFC] Invert sense of MIFlag::FPExcept flag.
Jan 9 2020, 6:40 PM · Restricted Project
pengfei accepted D72477: [TargetLowering][ARM][X86] Change softenSetCCOperands handling of ONE to avoid spurious exceptions for QNANs with strict FP quiet compares.

LGTM.

Jan 9 2020, 4:48 PM · Restricted Project

Jan 7 2020

pengfei committed rG9a621de1ecad: [X86] Adding fp128 support for strict fcmp (authored by pengfei).
[X86] Adding fp128 support for strict fcmp
Jan 7 2020, 9:20 PM
pengfei closed D71897: [X86] Adding fp128 support for strict fcmp.
Jan 7 2020, 9:20 PM · Restricted Project
pengfei updated the diff for D71897: [X86] Adding fp128 support for strict fcmp.

Add Fixme for softenSetCCOperands. We don't want to add extra logic code instead of pushing the libraries to do the right thing.
Address review comment.

Jan 7 2020, 7:32 PM · Restricted Project
pengfei added a comment to D71897: [X86] Adding fp128 support for strict fcmp.
Jan 7 2020, 7:32 PM · Restricted Project

Jan 2 2020

pengfei committed rG60333a531799: [X86] Enable strict FP by default and remove option -disable-strictnode… (authored by pengfei).
[X86] Enable strict FP by default and remove option -disable-strictnode…
Jan 2 2020, 7:03 PM
pengfei committed rG9dc9e0ea64f5: [X86] Optimization of inserting vxi1 sub vector into vXi1 vector (authored by pengfei).
[X86] Optimization of inserting vxi1 sub vector into vXi1 vector
Jan 2 2020, 5:29 PM
pengfei closed D71917: [X86] Optimization of inserting vxi1 sub vector into vXi1 vector .
Jan 2 2020, 5:29 PM · Restricted Project

Dec 30 2019

pengfei added a comment to D71897: [X86] Adding fp128 support for strict fcmp.

After a deeper investigation, I agreed with Craig that we should "expand the unsupported calls into multiple compares and control flow in IR". But I think we don't need libcalls. We can get sNaN, qNaN and compare results according to control flow and IRs. We only need to define a target dependent interface TLI.raiseFPException to handle exception respectively.

Dec 30 2019, 8:05 PM · Restricted Project

Dec 26 2019

pengfei accepted D71879: [X86] Custom widen 128/256-bit vXi32 fp_to_uint on avx512f targets without avx512vl. Similar for vXi64 on avx512dq without avx512vl..

LGTM.

Dec 26 2019, 6:42 PM · Restricted Project
pengfei added a comment to D71897: [X86] Adding fp128 support for strict fcmp.

There are libcalls for OGT/OLT/OLE/OGE that are always signalling. There is a libcall for OEQ/UNE that not signalling. And there's a libcall for Ordered/Unordered that is not signalling.

Is the signaling/no signaling action by design (the API guarantees the behavior) or depended on targets. I don't find the description about signaling on GCC document. I guess it depends on targets.

Note, that despite having multiple names there are really only 3 total libcalls. The names are aliases and the return value is used to check direction. The OGT/OLT/OLE/OGE libcall returns -1, 0, or 1. The other oeq/une and the ordered/unordered just return true or false.

In fact, there're only two. one is used for OGT/OLT/OLE/OGE/OEQ/ONE, one for ORD/UOR.
Why didn't we expand form these two functions directly? I think it can reduce the code complicity. And it can improve performance by reducing potential calls.

We may need to expand the unsupported calls into multiple compares and control flow in IR. For example for non-signalling ogt/olt/ole/oge we'll need to check unordered first and branch accordingly for qnans without calling the signalling ogt/olt/ole/oge libcall which will signal. Technically we could use a select to change the value we pass to the ogt/olt/ole/oge when its signalling, but select has to be expanded into control flow on many targets anyway. @uweigand, what are you thoughts on this?

I think it can be simplified to directly use __unordXf2 and __cmpXf2, if we know it's a NaN from the former, we can call a new function TLI.raiseNaNException to handle exception respectively.

Dec 26 2019, 5:53 PM · Restricted Project
pengfei created D71897: [X86] Adding fp128 support for strict fcmp.
Dec 26 2019, 6:21 AM · Restricted Project

Dec 25 2019

pengfei added a comment to D71879: [X86] Custom widen 128/256-bit vXi32 fp_to_uint on avx512f targets without avx512vl. Similar for vXi64 on avx512dq without avx512vl..

Do you have plan for uint_to _fp and signed i64? Otherwise, I can do it.

Dec 25 2019, 6:23 PM · Restricted Project
pengfei added inline comments to D71879: [X86] Custom widen 128/256-bit vXi32 fp_to_uint on avx512f targets without avx512vl. Similar for vXi64 on avx512dq without avx512vl..
Dec 25 2019, 5:19 PM · Restricted Project
pengfei added inline comments to D71879: [X86] Custom widen 128/256-bit vXi32 fp_to_uint on avx512f targets without avx512vl. Similar for vXi64 on avx512dq without avx512vl..
Dec 25 2019, 5:11 PM · Restricted Project
pengfei committed rG472bded3eda4: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend (authored by pengfei).
[X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend
Dec 25 2019, 4:34 PM
pengfei closed D71871: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend.
Dec 25 2019, 4:34 PM · Restricted Project
pengfei updated the diff for D71871: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend.

Minor fixup.

Dec 25 2019, 4:54 AM · Restricted Project
pengfei added inline comments to D71871: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend.
Dec 25 2019, 4:45 AM · Restricted Project
pengfei updated the diff for D71871: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend.

Address review comments.

Dec 25 2019, 4:36 AM · Restricted Project
pengfei created D71871: [X86] Enable STRICT_SINT_TO_FP/STRICT_UINT_TO_FP on X86 backend.
Dec 25 2019, 12:53 AM · Restricted Project

Dec 24 2019

pengfei added a comment to D71862: [WinEH] Delete addFnAttr("no-frame-pointer-elim") which seems no longer needed.
In D71862#1795767, @rnk wrote:
In D71862#1795756, @rnk wrote:

lgtm

Does funclet not need rbp to access parent local variables now?

No, it does need to go via ebp/rbp, but this attribute appears to no longer be required to achieve that.

Dec 24 2019, 5:24 PM · Restricted Project
pengfei added a comment to D71862: [WinEH] Delete addFnAttr("no-frame-pointer-elim") which seems no longer needed.
In D71862#1795756, @rnk wrote:

lgtm

Dec 24 2019, 5:15 PM · Restricted Project
pengfei accepted D71850: [X86] Add STRICT versions of CVTTP2SI, CVTTP2UI, CMPM, and CMPP..

Thanks. LGTM.

Dec 24 2019, 12:16 AM · Restricted Project

Dec 23 2019

pengfei added inline comments to D71850: [X86] Add STRICT versions of CVTTP2SI, CVTTP2UI, CMPM, and CMPP..
Dec 23 2019, 11:40 PM · Restricted Project
pengfei added inline comments to D71850: [X86] Add STRICT versions of CVTTP2SI, CVTTP2UI, CMPM, and CMPP..
Dec 23 2019, 9:49 PM · Restricted Project

Dec 22 2019

pengfei added inline comments to D71816: [DAGCombiner] Add combine for (not (strict_fsetcc)) to create a strict_fsetcc with the opposite condition..
Dec 22 2019, 6:40 PM · Restricted Project

Dec 18 2019

pengfei added inline comments to D71592: [X86] Enable STRICT_FP_TO_SINT/UINT on X86 backend. .
Dec 18 2019, 1:04 AM · Restricted Project

Dec 17 2019

pengfei committed rG8cc0b5867381: [X86] Add calculation for elements in structures in getting uniform base for… (authored by pengfei).
[X86] Add calculation for elements in structures in getting uniform base for…
Dec 17 2019, 8:29 PM
pengfei closed D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 17 2019, 8:29 PM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Address review comments.

Dec 17 2019, 8:01 PM · Restricted Project
pengfei committed rG1949235d13be: [X86] Add strict fma support (authored by pengfei).
[X86] Add strict fma support
Dec 17 2019, 7:52 PM
pengfei closed D71604: [X86] Add strict fma support.
Dec 17 2019, 7:52 PM · Restricted Project
pengfei updated the diff for D71604: [X86] Add strict fma support.

Address review comments.

Dec 17 2019, 6:07 PM · Restricted Project
pengfei added a comment to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Ping.

Dec 17 2019, 5:58 PM · Restricted Project
pengfei created D71604: [X86] Add strict fma support.
Dec 17 2019, 5:32 AM · Restricted Project

Dec 14 2019

pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Address review comments.

Dec 14 2019, 5:36 PM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 14 2019, 5:30 PM · Restricted Project
pengfei retitled D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic. from [X86] Check if source elements are not structures before using a uniform base for the Gather/Scatter intrinsic. to [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 14 2019, 7:13 AM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Removed unnecessary loop condition.
Added a vectorized index test.
Don't check if constant exist in DAG.

Dec 14 2019, 5:54 AM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Removed unnecessary else.

Dec 14 2019, 4:41 AM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Removed unnecessary assertions. Merged some common code.

Dec 14 2019, 4:32 AM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 14 2019, 3:21 AM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 14 2019, 3:12 AM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Optimized as Yuanke's suggestion.

Dec 14 2019, 1:42 AM · Restricted Project

Dec 13 2019

pengfei added a comment to D62731: Add support for options -frounding-math, -ftrapping-math, -ffp-model=, and -ffp-exception-behavior=, : Specify floating point behavior.

It's good that people are looking at achieving better modeling for the x86 backend, but we need to have a plan that doesn't require heroic effort just to get basic correctness.

Do you mean in the backend? If so, I don't think that's possible. The backends just don't have any sort of feature that could be used to get conservatively correct behavior for cheap the way intrinsics give it to us in the middle end. Once you go into instruction selection things get very low level in a hurry.

I'm looking for simple ways to modeling X86 intrinsics, but haven't find better one than modeling it one by one.

I would suggest that we need a function/call attribute roughly on the level of readonly / readnone, maybe readfponly, that says that a function has no side-effects and no dependencies on anything *except* the FP state.

Do you mean mark it at the declaration of intrinsics? Is it reasonable to mark except on dependent intrinsics?

Basic queries like Instruction::mayReadMemory() that are supposed to be used generically in code-motion transforms would then return true for calls marked that way only if they're FP-constrained functions.

Middle end or back end? I think in middle end you may need to change all releated passes to get such information to prevent optimization. And in back end, I think we can simply chain intrinsics marked except with other FP nodes like what common code doing.

Dec 13 2019, 6:10 PM · Restricted Project, Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 13 2019, 12:50 AM · Restricted Project

Dec 12 2019

pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 12 2019, 11:28 PM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

We don't need to check if constant is defined.

Dec 12 2019, 11:28 PM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Using gep_type_iterator to traverse.

Dec 12 2019, 9:52 PM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 12 2019, 9:52 PM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 12 2019, 7:46 PM · Restricted Project
pengfei added inline comments to D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 12 2019, 7:37 PM · Restricted Project
pengfei updated the diff for D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..

Updated to only check the final type.

Dec 12 2019, 7:10 PM · Restricted Project
pengfei created D71442: [X86] Add calculation for elements in structures in getting uniform base for the Gather/Scatter intrinsic..
Dec 12 2019, 4:29 PM · Restricted Project

Dec 10 2019

pengfei committed rG21bc8631fe93: [FPEnv][X86] Constrained FCmp intrinsics enabling on X86 (authored by pengfei).
[FPEnv][X86] Constrained FCmp intrinsics enabling on X86
Dec 10 2019, 4:27 PM
pengfei closed D70582: [FPEnv][X86] Constrained FCmp intrinsics enabling on X86.
Dec 10 2019, 4:27 PM · Restricted Project