similar to: RFC: Memcpy inlining in IR

Looks like there are a lot of opinions where memcpy expansion/inlining needs to happen: (late) IR, or if it is a backend problem, see also for example https://reviews.llvm.org/D35035. Complicating factor here is that efficient memcpy lowering is crucial for performance and code-size (and they occur a lot). Either way, I agree that the TLI hooks are not SelectionDAG specific, they can be used in

Hi all. I’m trying to get GlobalISel to work better with LTO. At the moment if you enable it via -fglobal-isel, it only adds the -mllvm -global-isel and related options to the cc1 invocation. With LTO, that doesn’t work as we need to encode codegen options into the bitcode, usually via function attributes. Does anyone have any ideas on how to achieve this? The only way I can see it working is if

I don’t know of any further issues preventing us flipping the switch. At this point, I’d aim to flip the switch shortly after the creation of the 6.0.0 release branch, so that GlobalISel can harden a bit more enabled-by-default on trunk before it goes into an LLVM release (presumably 7.0.0 then). Thanks, Kristof > On 11 Dec 2017, at 17:08, Amara Emerson <aemerson at apple.com> wrote:

Hi everyone, This RFC concerns the design and architecture of a generic machine instruction combiner/optimizer framework to be developed as part of the GISel pipeline. As we transition from correctness and reducing the fallback rate to SelectionDAG at -O0, we’re now starting to think about using GlobalISel with optimizations enabled. There are obviously many parts to this story as optimizations

Hi Amara, My reasons for preferring the switch to happen after the release branch is based on the following observations: * As far as I can see, the projects and products following top-of-trunk tend to test much more extensively than the testing that happens for llvm.org<http://llvm.org> releases. I expect that the llvm.org<http://llvm.org> release testing won’t find potential

> On Nov 13, 2017, at 11:53 AM, Vedant Kumar via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Hi Amara, > >> On Nov 10, 2017, at 9:12 AM, Amara Emerson via llvm-dev <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> wrote: >> >> Hi everyone, >> >> This RFC concerns the design and architecture of a generic machine

I’ve put up a patch here: https://reviews.llvm.org/D79769 <https://reviews.llvm.org/D79769> that adds a unified pipeline that targets can opt-into. It has some similarities with forcing fallbacks, but uses a different mechanism to do so to preserve the abort behavior. It therefore requires that every GISel pass needs to explicitly check whether the GISel selector is being requested rather

Thanks for the suggestions Vedant. Synthetic debug info is an interesting idea that sounds worthwhile. Could this be implemented as a “wrapper” pass that automatically decorates debug info before and after a specific pass run in opt (or pipeline of passes)? It might be useful to be able to easily enable this for a wide range of tests without having to manually modify each run line, perhaps as an

Hi GlobalISel interested parties, A recent bug report (https://bugs.llvm.org/show_bug.cgi?id=40968) on AArch64 exposed a problem with our modeling of intrinsic semantics when dealing with type overloaded calls. The crux of the matter is that because GlobalISel’s LowLevelTypes only carry size and vector layout information, and not any information about whether a type is integer or fp, we lose

FYI all: the patch to enable it is available to review here: https://reviews.llvm.org/D41362 Thanks, Amara > On Dec 18, 2017, at 5:44 PM, Amara Emerson via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Ok. We’ll look at what we can do to further stress test it in the next two months, additional suggestions from the community is welcome. Patch should be incoming to enable it

On 18 Dec 2017, at 15:11, Amara Emerson <aemerson at apple.com<mailto:aemerson at apple.com>> wrote: On Dec 18, 2017, at 12:37 PM, Kristof Beyls <Kristof.Beyls at arm.com<mailto:Kristof.Beyls at arm.com>> wrote: Hi Amara, My reasons for preferring the switch to happen after the release branch is based on the following observations: * As far as I can see, the

Hi all, Over the past few months we’ve been doing work on the foundations for the next stages of GlobalISel development. In terms of changes from this time last year, the IR translator, the legalizer, and instruction selector have seen moderate to major changes. The most significant of these was the change to the legalizer API, allowing targets to use predicates to express legality, which gives

> On May 5, 2020, at 2:45 PM, Ties Stuij <Ties.Stuij at arm.com> wrote: > > Quentin: Thanks for the info. I was under the impression that the LLVM community at large would prefer to extend the IR type to a bfloat MVT type. I've made a number of patches to implement this up to a point for AArch64. I can post those on Phab and start a thread to sample opinions. Sounds good to

Unless there are still open issues with your patch, or our internal bots point to problems, I think time has come to flip the switch. Thanks Gerolf > On Dec 18, 2017, at 11:14 AM, Amara Emerson via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > FYI all: the patch to enable it is available to review here: https://reviews.llvm.org/D41362 <https://reviews.llvm.org/D41362>

Thanks all. Amara, could you take a look? > On Nov 20, 2017, at 3:06 AM, Oliver Stannard <oliver.stannard at arm.com> wrote: > > Hi Quentin, > > I’ve raised: > https://bugs.llvm.org/show_bug.cgi?id=35359 <https://bugs.llvm.org/show_bug.cgi?id=35359> > https://bugs.llvm.org/show_bug.cgi?id=35360 <https://bugs.llvm.org/show_bug.cgi?id=35360> >

> On Nov 10, 2017, at 10:19 AM, Hal Finkel via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > > On 11/10/2017 11:12 AM, Amara Emerson via llvm-dev wrote: >> Hi everyone, >> >> This RFC concerns the design and architecture of a generic machine instruction combiner/optimizer framework to be developed as part of the GISel pipeline. As we transition from

I don’t think bfloat should be handled this way. What Amara is suggesting is an optimization, i.e., if we drop the information we are still correct. With bfloat, if we do an operation on float16 instead of bfloat16 this is a correctness problem. So that means that either we need to have new opcodes for bfloat or we need to carry around the floating point type in MIR. I think it would be more

> On 30 Jul 2018, at 16:04, Quentin Colombet via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Hi Amara, > > Thanks for sharing the plan going forward. > > Inlined a couple of comments. > > 2018-07-30 7:01 GMT-07:00 Amara Emerson via llvm-dev <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>>: >> Hi all, >> >>

> On 2 Aug 2018, at 14:50, Quentin Colombet <quentin.colombet at gmail.com> wrote: > > Hi Daniel, > > 2018-07-31 8:40 GMT-07:00 Daniel Sanders <daniel_l_sanders at apple.com>: >> >> >> On 30 Jul 2018, at 16:04, Quentin Colombet via llvm-dev >> <llvm-dev at lists.llvm.org> wrote: >> >> Hi Amara, >> >> Thanks for

Hi all, I'm trying to get GlobalISel up and running on an off-tree architecture and am thinking I must be doing something wrong, given by how few things actually work. Namely, any ImmLeaf pattern will fail to match if there is a (TRUNC/ZEXT/SEXT) applied to the constant operand, all of which are commonly created through Legalization. This is due to G_CONSTANT being explicitly looked for by