similar to: DFAPacketizer, Scheduling and LoadLatency

> In particular, the LoadLatency is used in defaultDefLatency: > > /// Return the default expected latency for a def based on it's opcode. > unsigned TargetInstrInfo::defaultDefLatency( > const MCSchedModel &SchedModel, const MachineInstr *DefMI) const { > if (DefMI->isTransient()) > return 0; > if (DefMI->mayLoad()) > return

On Tue, Nov 17, 2015 at 11:15 AM, Krzysztof Parzyszek < kparzysz at codeaurora.org> wrote: > On 11/17/2015 12:26 PM, Rail Shafigulin wrote: > >> >> I tried setting >> let mayLoad = 1 { >> class InstrLD .... { >> } >> } >> >> But that didn't seem to work. When I looked at the debug output the >> latency for the load

On Apr 26, 2013, at 3:53 AM, Martin J. O'Riordan <Martin.ORiordan at movidius.com> wrote: > I am migrating the llvm/clang derived compiler for our processor from the > v3.1 to v3.2 codebase. This has mostly gone well except that instruction > latency scheduling is no longer happening. > > The people who implemented this previously sub-classed 'ScheduleDAGInstrs'

I'm trying to create a simplified 2 slot VLIW from an OR1K. The codebase I'm working with is here <https://github.com/openrisc/llvm-or1k>. I've created an initial MyTargetSchedule.td def MyTargetModel : SchedMachineModel { // HW can decode 2 instructions per cycle. let IssueWidth = 2; let LoadLatency = 4; let MispredictPenalty = 16; // This flag is set to allow the

Jonas, At this point, the DFA packetizer models a simple VLIW architecture and does not accommodate multiple stages. That's the reason for the behavior you're seeing. -Anshu --- Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, hosted by The Linux Foundation *From:*llvmdev-bounces at cs.uiuc.edu [mailto:llvmdev-bounces at cs.uiuc.edu] *On Behalf Of *Jonas

Hi, I looked a bit through the mail archives, and found this question answered in Oct 2011 (see below). It is interesting to find this in the ARM backend, considering your answer. Can you give more information about for example is this a temporary deficiency in the DFAPacketizer? What is the IIC_iMOVi itinerary doing below? Thanks, Jonas Thu Oct 6 15:11:25 CDT 2011: Hello Hal. > Is there

Hi Jonas, > It is interesting to find this in the ARM backend, considering your answer. The ARM backend doesn't use the DFA packetizer. It's only used by Hexagon. At this point, there is no plan to address thisin the DFA packetizer since none of the supported targets needthe functionality. Thanks -Anshu --- Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,

Hi Anshu, Would there be any interest in extending this algorithm to handling more extensive models, such as VLIW scheduling based on FU's and bundle space... ie handle multiple stages ? I might do it and commit, if there is acceptance and guidance... Jonas ________________________________ From: Anshuman Dasgupta [mailto:adasgupt at codeaurora.org] Sent: Tuesday, February 12, 2013 4:47 PM

So if I use the SchedMachineModel method, can I just skip itineraries? Phil On Wed, Apr 20, 2016 at 12:29 PM, Sergei Larin <slarin at codeaurora.org> wrote: > Target does make a difference. VLIW needs more hand-holding. For what you > are describing it should be fairly simple. > > > > Best strategy – see what other targets do. ARM might be a good start for > generic

Hi Phil. You more or less answered your own question, but let me give you some more info. Maybe it is of use. >From what I understand the SchedMachineModel is the future, although it is not as powerful as itineraries at present. The mi-scheduler is mostly developed around out-of-orders cores, I believe (I love to hear arguments on the contrary). Some of the constraints that can be found in

Sure I will split it and put it in two patches. Give me few hours. I need to test those patches. Sirish On 4/19/2012 8:40 AM, Tom Stellard wrote: > On Wed, Apr 18, 2012 at 11:18:05PM -0500, Sirish Pande wrote: >> Hi, >> >> Here's a patch for Hexagon Packetizer for review. This patch does >> not yield any warnings. >> > Would it be possible to split this

Hi, I am having problems writing the ProcessorItineraries list. As instructions on my VLIW target have varying size I want to model both cpu units and bundle bits as FUs. The following does not work, to my surprise: InstrItinData<ALU, [InstrStage<1, [BITS1,BITS2, BITS3, BITS4], 0>, InstrStage<1, [ALU1, ALU2]>]> I want to express that there are

Hello LLVM Developers, We are working on extending currently available register rematerialization to include cases where sequence of multiple instructions is required to rematerialize a value. We had a discussion on this in community mailing list and link is here: http://lists.llvm.org/pipermail/llvm-dev/2016-September/subject.html#104777 >From the above discussion and studying the code we

Hi everyone, The MachineLICM pass has a heuristic such that, even in low-register-pressure situations, it will refuse to hoist "cheap" instructions out of loops. By default, when an itinerary is available, this means that all of the defined operands are available in at most 1 cycle. ARM overrides this, and provides this more-customized definition: bool ARMBaseInstrInfo::

On Oct 21, 2011, at 12:15 AM, James Molloy wrote: > Hi Andy, > > Could you describe how this would be done? In the current ARM itineraries > (say C-A9 for example), the superscalar issue stage is modelled as taking 1 > cycle. If it were to take 2 cycles instead, as far as I can tell the hazard > analyser would stall because both FU's would be acquired. > > I would

In our architecture loads from certain memory locations take a long time to complete (on the order of 150 clock cycles). Since we don't have a way to tell at compile time if the address being loaded from lies in slow or fast memory, I've gone ahead and made all of the load numbers high, such as: InstrItinData< II_LOAD1, [InstrStage<150, [AGU]>]>, However, I see that

Hi Andy, Thanks for the explanations. Yes AMDGPU is in-order and has MicroOpBufferSize = 1. Re "issue limited" and instruction groups: could it make sense to disable the generic scheduler's detection of issue limitation on in-order CPUs, or on CPUs that don't define instruction groups, or some similar condition? Something like: --- a/lib/CodeGen/MachineScheduler.cpp +++

On Tue, 16 Jun 2020 at 15:47, Tim Northover <t.p.northover at gmail.com> wrote: > > On Tue, 16 Jun 2020 at 10:23, Prathamesh Kulkarni via llvm-dev > <llvm-dev at lists.llvm.org> wrote: > > (b) Modifies RegisterCoalescer::reMaterializeTrivialDef and > > TargetInstrInfo::isReallyTriviallyReMaterializableGeneric to check > > for single live def, instead of

> On Jun 28, 2017, at 5:10 PM, Quentin Colombet via llvm-dev <llvm-dev at lists.llvm.org> wrote: > > Oh wait, vreg1 is indeed used. > Yeah, having a dead flag here sounds wrong. I mean on the instruction itself. On the bundle, that’s debatable. That would fit the semantic “if no side effect you can kill it” (here there is side effect, we define other vregs). > >> On

I overrode getInstrLatency and did some printing to see what is available there. It looks like the registers are still virtual at that point when getInstrLatency is called - is that correct? (we needed to make some decisions based on actual registers that have been assigned since some registers are reserved as address space pointers and we could vary the latency based on which address space