- User Since
- Jan 9 2018, 7:56 AM (88 w, 3 d)
Tue, Sep 10
Fri, Sep 6
Added condition in foldOperands to allow tied subreg folding
for V_FMAC and V_MAC operations
Thu, Aug 29
Wed, Aug 28
Tue, Aug 27
Fri, Aug 23
Forgot to capitalize var name.
Set bool in condition.
Made some changes to code.
Added test case
Aug 20 2019
This has been copied over and extended on in https://reviews.llvm.org/D62802 so I'm abandoning this revision.
Jul 25 2019
Hmm... looks like AMDGPUISelLowering.cpp has changed quite a bit in regards to the calling convention.
Jul 23 2019
Remove underline to ref hyperlink from invariant.group
Removed preceding underline to ref hyperlink.
Jul 22 2019
Added hyperlinks to LangRef.rst
Changed LangRef.rst: Moved !dereferenceable and !dereferenceable_or_null to their
own section in Metadata and pointed inttoptr and load to that section.
Jul 20 2019
Added IntToPtrInst to case statement in Value::getPointerDereferenceableBytes
Changed LangRef.rst to reflect !dereferenceable is applicable to pointer types not
just load types.
Updated error comment and case error test
Jul 19 2019
Changed error message in AnalyzeFormalArguments to be more generic.
Fixed test to use llvm-as and to just check for passing.
Added !dereferenceable_or_null to syntax of inttoptr in LangRef
Added tests and updated LangRef
Added test case. Changed assert to report_fatal_error when checking
arguments and returns.
Jul 18 2019
Jun 26 2019
Jun 22 2019
Jun 20 2019
Suggested changes: Added InstrMapping. Three test files. Lower-cased suffixes for MI defs. Changed multiclass suffix.
Jun 19 2019
Changes per suggestions
Jun 18 2019
May 15 2019
May 10 2019
Added test for SGPR tuple
May 7 2019
More detailed explanation of why LCSSA is needed
May 6 2019
Added StackProtectorID and changed LCSSA to use it instead of StackProtector directly.
May 2 2019
Fixed 105 SGPR to 106 SGPR, increased limit count for allocateSGPRTuple
Preserving StackProtector in LCSSA to avoid pass scheduling conflict
Removed explicit call of LCSSA in AMDGPUTargetMachine
Scratch that last commit, this is still broken.
I was misunderstanding the dependency issues, this should fix it.
Apr 30 2019
[AMDGPU] Increased SGPR Count for Calling Convention
Apr 29 2019
Apr 25 2019
Apr 23 2019
Moved LCSSA call to after the sinking pass.
Apr 17 2019
We have a test case such that a value that is uniform in the loop is used outside the loop where threads might have diverged.
Mar 20 2019
Mar 19 2019
Mar 12 2019
Add requested changes
Mar 11 2019
Mar 6 2019
Mar 5 2019
Mar 4 2019
Feb 27 2019
Rename function to better reflect what it does