stefanp (Stefan Pintilie)
User

Projects

User does not belong to any projects.

User Details

User Since
May 29 2017, 8:02 AM (72 w, 1 d)

Recent Activity

Wed, Oct 10

stefanp updated the diff for D42590: [PowerPC] Try to move the stack pointer update instruction later in the prologue and earlier in the epilogue (Version 2).

I'm sorry it took so long for me to look at this review.

Wed, Oct 10, 1:08 PM

Fri, Oct 5

stefanp updated the diff for D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.

Addressed review comments.

Fri, Oct 5, 12:16 PM

Thu, Oct 4

stefanp updated the diff for D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.

Removed the custom PPCISD node and it simplified the patch considerably.

Thu, Oct 4, 11:14 AM

Mon, Oct 1

stefanp committed rL343525: [PowerPC] Folding XForm to DForm loads requires alignment for some DForm loads..
[PowerPC] Folding XForm to DForm loads requires alignment for some DForm loads.
Mon, Oct 1, 1:18 PM
stefanp closed D51988: [PowerPC] Folding XForm to DForm loads requires alignment for some DForm loads..
Mon, Oct 1, 1:18 PM
stefanp updated the diff for D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.

Address Review Comments

Mon, Oct 1, 12:24 PM

Fri, Sep 28

stefanp updated the diff for D51988: [PowerPC] Folding XForm to DForm loads requires alignment for some DForm loads..

Moved condition to the correct location and added a test case.

Fri, Sep 28, 2:33 PM

Mon, Sep 24

stefanp committed rL342911: [Power9] [CLANG] Add __float128 exponent GET and SET builtins.
[Power9] [CLANG] Add __float128 exponent GET and SET builtins
Mon, Sep 24, 11:16 AM
stefanp committed rC342911: [Power9] [CLANG] Add __float128 exponent GET and SET builtins.
[Power9] [CLANG] Add __float128 exponent GET and SET builtins
Mon, Sep 24, 11:16 AM
stefanp closed D48184: [Power9] [CLANG] Add __float128 exponent GET and SET builtins.
Mon, Sep 24, 11:16 AM
stefanp committed rL342910: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.
[Power9] [LLVM] Add __float128 exponent GET and SET builtins
Mon, Sep 24, 11:16 AM
stefanp closed D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.
Mon, Sep 24, 11:16 AM

Sep 12 2018

stefanp created D51988: [PowerPC] Folding XForm to DForm loads requires alignment for some DForm loads..
Sep 12 2018, 7:28 AM

Sep 10 2018

stefanp updated the diff for D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.

Update patch based on reviewer comments.

Sep 10 2018, 1:25 PM

Aug 27 2018

stefanp added a comment to D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..

I'm not 100% sure if we can remove the default option -funwind-tables for x86.
I know that using -funwind-tables prevents (or hides) this issue but it may be required for another reason that this fix does not cover. I don't actually know what the initial intention was when that default was added.
I think that someone on the x86 side would be a better judge of this.

Aug 27 2018, 5:43 AM

Aug 24 2018

stefanp committed rL340643: [PowerPC] Emit xscpsgndp instead of xxlor when copying floating point scalar….
[PowerPC] Emit xscpsgndp instead of xxlor when copying floating point scalar…
Aug 24 2018, 1:01 PM
stefanp closed D50004: [PowerPC] Emit xscpsgndp instead of xxlor when copying floating point scalar registers for P9.
Aug 24 2018, 1:01 PM
stefanp committed rL340641: [Exception Handling] Unwind tables are required for all functions that have an….
[Exception Handling] Unwind tables are required for all functions that have an…
Aug 24 2018, 12:40 PM
stefanp closed D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..
Aug 24 2018, 12:39 PM
stefanp committed rL340639: [PowerPC] Change Test Options [NFC].
[PowerPC] Change Test Options [NFC]
Aug 24 2018, 12:25 PM
stefanp reopened D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..
Aug 24 2018, 11:00 AM
stefanp committed rL340625: Revert "[Exception Handling] Unwind tables are required for all functions that….
Revert "[Exception Handling] Unwind tables are required for all functions that…
Aug 24 2018, 10:28 AM
stefanp added a reverting commit for rL340614: [Exception Handling] Unwind tables are required for all functions that have an…: rL340625: Revert "[Exception Handling] Unwind tables are required for all functions that….
Aug 24 2018, 10:28 AM
stefanp committed rL340614: [Exception Handling] Unwind tables are required for all functions that have an….
[Exception Handling] Unwind tables are required for all functions that have an…
Aug 24 2018, 8:52 AM
stefanp closed D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..
Aug 24 2018, 8:52 AM

Aug 22 2018

stefanp updated the diff for D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..

Sorry about that. I should have added the test cases earlier.

Aug 22 2018, 12:15 PM

Aug 20 2018

stefanp updated the diff for D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.

Added test case.
Address reviewers comments.

Aug 20 2018, 1:46 PM
stefanp created D50987: [Exception Handling] Unwind tables are required for all functions that have an EH personality..
Aug 20 2018, 12:17 PM
stefanp abandoned D50908: [PowerPC] Enable -funwind-tables by default on powerpc.

Determined this is not the correct way to solve this problem.
Going to abandon this change.

Aug 20 2018, 11:38 AM

Aug 17 2018

stefanp added a comment to D50908: [PowerPC] Enable -funwind-tables by default on powerpc.

GCC does call the exception handler correctly for this example. However, it does not (at least not that I can tell) have a default option like the one llvm uses -funwind-tables.

Aug 17 2018, 12:20 PM
stefanp created D50908: [PowerPC] Enable -funwind-tables by default on powerpc.
Aug 17 2018, 9:54 AM
stefanp committed rL340037: [PowerPC] Generate lxsd instead of the ld->mtvsrd sequence for vector loads.
[PowerPC] Generate lxsd instead of the ld->mtvsrd sequence for vector loads
Aug 17 2018, 8:16 AM
stefanp closed D49698: [PowerPC] Generate lxsd instead of the ld->mtvsrd sequence for vector loads.
Aug 17 2018, 8:16 AM

Aug 8 2018

stefanp commandeered D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.
Aug 8 2018, 11:00 AM

Jul 19 2018

stefanp committed rL337488: [Power9] Code Cleanup - Remove needsAggressiveScheduling().
[Power9] Code Cleanup - Remove needsAggressiveScheduling()
Jul 19 2018, 12:39 PM
stefanp closed D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().
Jul 19 2018, 12:39 PM

Jul 18 2018

stefanp created D49507: [Power9] Add __float128 support in the backend for bitcast to a i128.
Jul 18 2018, 1:20 PM

Jul 12 2018

stefanp committed rL336940: [PowerPC] [NFC] Update __float128 tests.
[PowerPC] [NFC] Update __float128 tests
Jul 12 2018, 1:24 PM

Jul 10 2018

stefanp abandoned D48526: [Power9] Add six __float128 builtins found in gcc.

We have determined that we do not require these builtin names.

Jul 10 2018, 6:55 PM
stefanp committed rL336754: [Power9] Add remaining __flaot128 builtin support for FMA round to odd.
[Power9] Add remaining __flaot128 builtin support for FMA round to odd
Jul 10 2018, 6:47 PM
stefanp closed D48218: [Power9] Add remaining __flaot128 builtin support for FMA round to odd.
Jul 10 2018, 6:47 PM
stefanp added a comment to D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.

I looked into the naming of those builtins.
GCC does document the overloaded versions of those functions:
scalar_extract_exp for __builtin_vsx_scalar_extract_expq
scalar_insert_exp for __builtin_vsx_scalar_insert_exp_qp

Jul 10 2018, 10:17 AM

Jul 9 2018

stefanp committed rL336601: [Power9] Add __float128 builtins for Rounding Operations.
[Power9] Add __float128 builtins for Rounding Operations
Jul 9 2018, 1:43 PM
stefanp closed D48415: [Power9] Add __float128 builtins for Rounding Operations.
Jul 9 2018, 1:43 PM
stefanp committed rL336596: [Power9] [CLANG] Add __float128 support for trunc to double round to odd.
[Power9] [CLANG] Add __float128 support for trunc to double round to odd
Jul 9 2018, 1:15 PM
stefanp committed rC336596: [Power9] [CLANG] Add __float128 support for trunc to double round to odd.
[Power9] [CLANG] Add __float128 support for trunc to double round to odd
Jul 9 2018, 1:14 PM
stefanp closed D48482: [Power9] [CLANG] Add __float128 support for trunc to double round to odd.
Jul 9 2018, 1:14 PM
stefanp committed rL336595: [Power9] [LLVM] Add __float128 support for trunc to double round to odd.
[Power9] [LLVM] Add __float128 support for trunc to double round to odd
Jul 9 2018, 1:14 PM
stefanp closed D48483: [Power9] [LLVM] Add __float128 support for trunc to double round to odd.
Jul 9 2018, 1:14 PM
stefanp committed rC336579: [Power9] Add __float128 builtins for Round To Odd.
[Power9] Add __float128 builtins for Round To Odd
Jul 9 2018, 11:55 AM
stefanp committed rL336579: [Power9] Add __float128 builtins for Round To Odd.
[Power9] Add __float128 builtins for Round To Odd
Jul 9 2018, 11:55 AM
stefanp closed D47548: [Power9] Add __float128 builtins for Round To Odd.
Jul 9 2018, 11:55 AM
stefanp closed D47548: [Power9] Add __float128 builtins for Round To Odd.
Jul 9 2018, 11:55 AM
stefanp committed rL336578: [Power9] Add __float128 builtins for Round To Odd.
[Power9] Add __float128 builtins for Round To Odd
Jul 9 2018, 11:55 AM
stefanp closed D47550: [Power9] Add __float128 builtins for Round To Odd.
Jul 9 2018, 11:55 AM
stefanp committed rL336548: [Power9] Add __float128 support for compare operations.
[Power9] Add __float128 support for compare operations
Jul 9 2018, 6:41 AM
stefanp closed D48294: [Power9] Add __float128 support for compare operations.
Jul 9 2018, 6:41 AM

Jul 5 2018

stefanp committed rL336406: [Power9] Add __float128 library call for frem.
[Power9] Add __float128 library call for frem
Jul 5 2018, 7:52 PM
stefanp closed D48552: [Power9] Add __float128 library call for frem.
Jul 5 2018, 7:51 PM
stefanp updated the diff for D48294: [Power9] Add __float128 support for compare operations.

Added handling for the select f128.
Unlike the double type, the __float128 type cannot not use the fsel instruction but we should still expand it to something that functions correctly.

Jul 5 2018, 12:38 PM
stefanp closed D45265: [PowerPC] Replace the Post RA List Scheduler with the Machine Scheduler.

Done.
Committed in revision: rL336295

Jul 5 2018, 7:00 AM

Jul 4 2018

stefanp committed rL336295: [PowerPC] Replace the Post RA List Scheduler with the Machine Scheduler.
[PowerPC] Replace the Post RA List Scheduler with the Machine Scheduler
Jul 4 2018, 11:59 AM
stefanp added a comment to D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().

Hi Hal, Eric,

Jul 4 2018, 10:48 AM

Jun 29 2018

stefanp added a comment to D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().

Hi Eric,

Jun 29 2018, 6:43 AM

Jun 28 2018

stefanp updated the diff for D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().

Fixed comments according to previous review.

Jun 28 2018, 12:33 PM

Jun 27 2018

stefanp updated the diff for D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().

Updated the comments.
Sorry.. I should have caught them initially.

Jun 27 2018, 1:34 PM
stefanp added a comment to D45265: [PowerPC] Replace the Post RA List Scheduler with the Machine Scheduler.

Sorry for the late reply. I have been distracted with something else for a little while.
I have added the patch to remove needsAggressiveScheduling() here:
https://reviews.llvm.org/D48663

Jun 27 2018, 11:09 AM
stefanp created D48663: [Power9] Code Cleanup - Remove needsAggressiveScheduling().
Jun 27 2018, 11:06 AM

Jun 25 2018

stefanp added a dependency for D48552: [Power9] Add __float128 library call for frem: D47552: [Power9] Implement float128 parameter passing and return values.
Jun 25 2018, 10:36 AM
stefanp added a dependent revision for D47552: [Power9] Implement float128 parameter passing and return values: D48552: [Power9] Add __float128 library call for frem.
Jun 25 2018, 10:36 AM
stefanp created D48552: [Power9] Add __float128 library call for frem.
Jun 25 2018, 10:35 AM

Jun 23 2018

stefanp created D48526: [Power9] Add six __float128 builtins found in gcc.
Jun 23 2018, 5:49 PM

Jun 22 2018

stefanp created D48483: [Power9] [LLVM] Add __float128 support for trunc to double round to odd.
Jun 22 2018, 6:49 AM
stefanp created D48482: [Power9] [CLANG] Add __float128 support for trunc to double round to odd.
Jun 22 2018, 6:47 AM

Jun 20 2018

stefanp created D48415: [Power9] Add __float128 builtins for Rounding Operations.
Jun 20 2018, 7:32 PM

Jun 19 2018

stefanp updated the diff for D48294: [Power9] Add __float128 support for compare operations.

Fixed test case command.

Jun 19 2018, 1:02 PM

Jun 18 2018

stefanp created D48294: [Power9] Add __float128 support for compare operations.
Jun 18 2018, 12:42 PM

Jun 15 2018

stefanp added a dependency for D48218: [Power9] Add remaining __flaot128 builtin support for FMA round to odd: D47550: [Power9] Add __float128 builtins for Round To Odd.
Jun 15 2018, 7:00 AM
stefanp added a dependent revision for D47550: [Power9] Add __float128 builtins for Round To Odd: D48218: [Power9] Add remaining __flaot128 builtin support for FMA round to odd.
Jun 15 2018, 7:00 AM
stefanp created D48218: [Power9] Add remaining __flaot128 builtin support for FMA round to odd.
Jun 15 2018, 7:00 AM

Jun 14 2018

stefanp added a dependency for D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins: D47550: [Power9] Add __float128 builtins for Round To Odd.
Jun 14 2018, 12:02 PM
stefanp added a dependent revision for D47550: [Power9] Add __float128 builtins for Round To Odd: D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.
Jun 14 2018, 12:02 PM
stefanp added a dependency for D48184: [Power9] [CLANG] Add __float128 exponent GET and SET builtins: D47550: [Power9] Add __float128 builtins for Round To Odd.
Jun 14 2018, 12:01 PM
stefanp added a dependent revision for D47550: [Power9] Add __float128 builtins for Round To Odd: D48184: [Power9] [CLANG] Add __float128 exponent GET and SET builtins.
Jun 14 2018, 12:01 PM
stefanp created D48185: [Power9] [LLVM] Add __float128 exponent GET and SET builtins.
Jun 14 2018, 11:58 AM
stefanp created D48184: [Power9] [CLANG] Add __float128 exponent GET and SET builtins.
Jun 14 2018, 11:56 AM

Jun 13 2018

stefanp committed rL334613: [PowerPC] The __float128 type should only be available on Power9.
[PowerPC] The __float128 type should only be available on Power9
Jun 13 2018, 9:09 AM
stefanp committed rC334613: [PowerPC] The __float128 type should only be available on Power9.
[PowerPC] The __float128 type should only be available on Power9
Jun 13 2018, 9:09 AM
stefanp closed D48088: [PowerPC] The __float128 type should only be available on Power9.
Jun 13 2018, 9:09 AM

Jun 12 2018

stefanp created D48088: [PowerPC] The __float128 type should only be available on Power9.
Jun 12 2018, 12:06 PM

Jun 11 2018

stefanp updated the diff for D47548: [Power9] Add __float128 builtins for Round To Odd.

Updated the test case to use clang cc1 instead of just clang.

Jun 11 2018, 8:40 AM

May 31 2018

stefanp added a comment to D47550: [Power9] Add __float128 builtins for Round To Odd.

@lattner
Added Chris Lattner as a reviewer in case I did something silly in the target indep code.

May 31 2018, 12:14 PM
stefanp added a reviewer for D47550: [Power9] Add __float128 builtins for Round To Odd: lattner.
May 31 2018, 12:13 PM
stefanp updated the diff for D47550: [Power9] Add __float128 builtins for Round To Odd.

Fixed some of the style issues.

May 31 2018, 12:12 PM
stefanp added a dependent revision for D47550: [Power9] Add __float128 builtins for Round To Odd: D47548: [Power9] Add __float128 builtins for Round To Odd.
May 31 2018, 11:36 AM
stefanp added a dependency for D47548: [Power9] Add __float128 builtins for Round To Odd: D47550: [Power9] Add __float128 builtins for Round To Odd.
May 31 2018, 11:36 AM
stefanp updated the summary of D47550: [Power9] Add __float128 builtins for Round To Odd.
May 31 2018, 11:35 AM

May 30 2018

stefanp created D47550: [Power9] Add __float128 builtins for Round To Odd.
May 30 2018, 11:51 AM
stefanp created D47548: [Power9] Add __float128 builtins for Round To Odd.
May 30 2018, 11:49 AM

May 22 2018

stefanp added a comment to D45265: [PowerPC] Replace the Post RA List Scheduler with the Machine Scheduler.

Hi Eric,

May 22 2018, 10:55 AM