- User Since
- Jul 18 2018, 9:45 PM (57 w, 2 d)
Thu, Aug 22
This is a WIP draft and I have not fixed all check-all cases now. I want to get some quick feedback whether it's on the right direction and whether its performance is good at all different target. If you have time, could you please review it or give some comments, and help me to verify the performance at other targets?
Thu, Aug 15
Wed, Aug 14
Is there any fix patch proposed to track/fix the regression? @dnsampaio
Mon, Aug 12
Thu, Aug 8
Should this good patch be rebased and continued to move on? @wmi
it'd be better to move on this work because D27366 is abandoned and D34608 is not updated for a long time, and those 3 patches are all trying to fix same issue and not landed successfully.
It would be great If it can land.
Mon, Aug 5
Sun, Aug 4
Should this be rebased and continued to move on? Or it already could be addressed by https://reviews.llvm.org/D41765?
Wed, Jul 31
Because we have PPCVSXSwapRemoval pass to hack the element order before P9 with vsx, the element order is not always standard normal order in register.
And the optimization of this patch will be conflict with PPCVSXSwapRemoval so that we can not get correct result during the process. The fix way is to not do this optmization before P9.
update patch due to find issue.
Tue, Jul 30
Sorry to forget to add revision address in commit. Close it manually.
Mon, Jul 29
Commit testcase firstly and address comments.
Fri, Jul 26
Jul 25 2019
Jul 24 2019
Jul 22 2019
Jul 21 2019
Jul 17 2019
After run bmk 2017 cpu for fortran and c/c++, there is some noise, no obvious degression. Some have little improvement about 1%~2%.
Jul 16 2019
Jul 15 2019
gentle pin... It's a follow-up of https://reviews.llvm.org/D60601
Jul 4 2019
Jul 3 2019
Jul 1 2019
Jun 28 2019
Jun 27 2019
I have another question about any_*.
Jun 25 2019
Is there any further step to enable the rounding-mode infra to handle rounding mode metadata in intrinsics? For example, covert rounding mode metadata to a new constant operand of strict_* series op. If some target/platform does not have related machine instruction for different static rounding-mode, then ignore this constant in td selection.
Jun 11 2019
Jun 5 2019
That (controlling within the headers) sounds good to me. When that lands, then my understanding is that the PPCLinuxToolChain code would be adjusted to include ppc_wrappers in the search path in the general case. Please let me know if that's not the case. Thanks.
Jun 4 2019
Jun 2 2019
May 30 2019
add test/CodeGen/ppc-mm-malloc-le.c, and use UNSUPPORTED: test flag to disable unsupport test of mm-malloc.
May 29 2019
May 28 2019
Thanks. I will commit for @qiucf
May 24 2019
Apr 29 2019
update diff since it's out-of-date.