search for: machineschedstrategi

...that knows how to construct a custom ScheduleDAGInstrs. This is an easy way to reuse the standard scheduling pass and DAG builder. The driver will determine the scheduling region, but everything else is customizable. 3. New scheduling algorithms can be introduced by implementing new MachineSchedStrategies. We can add a target hook to select the strategy if needed. There's still plenty of opportunity to restructure the code and add customization points. Keep in mind that the goal for the target independent code is clarity and maintainability. Code reuse across custom schedulers is secondar...

On May 9, 2013, at 4:02 AM, Fraser Cormack <fraser at codeplay.com> wrote: > I have an instruction that takes no operands, and produces two results, in two consecutive cycles. > > I tried both of the following to my Schedule.td file: > > InstrItinData<IIMyInstr, [InstrStage<2, [FuncU]>], [1, 2]>, > InstrItinData<IIMyInstr, [InstrStage<1,

On 09/05/2013 18:25, Andrew Trick wrote: > > On May 9, 2013, at 4:02 AM, Fraser Cormack <fraser at codeplay.com > <mailto:fraser at codeplay.com>> wrote: > >> I have an instruction that takes no operands, and produces two >> results, in two consecutive cycles. >> >> I tried both of the following to my Schedule.td file: >> >>

Hi Andrew, I seem to be making good progress on the P5600 scheduler using the new machine model but I've got a few questions about it. How would you represent an instruction that splits into two micro-ops and is dispatched to two different reservation stations? For example, I have two reservation stations (AGQ and FPQ). An FPU load instruction is split into a load micro-op which is

Hey Everyone, I'd like to begin a project to rework the scheduler to address some problems we've discovered on this end. The goal is to get a more configurable/flexible scheduler while simplifying maintenance by separating policy from implementation to get independent and interchangeable parts. This is going to be challenging because we are still stuck on LLVM 2.9. We will be upgrading

I have an instruction that takes no operands, and produces two results, in two consecutive cycles. I tried both of the following to my Schedule.td file: InstrItinData<IIMyInstr, [InstrStage<2, [FuncU]>], [1, 2]>, InstrItinData<IIMyInstr, [InstrStage<1, [FuncU]>, InstrStage<1, [FuncU]>], [1, 2]>, From what I can see in examples, these say that the first

On Jun 3, 2013, at 9:42 AM, Steve Montgomery <stephen.montgomery3 at btinternet.com> wrote: > Hi Jakob, > > thanks for the advice. I'll do as you suggest and make sure that CCR is never live. > > I can use pseudo-instructions to bundle cmp+jump but it's not ideal because I might also have to bundle cmp+jump+jump+... into a pseudo. Also, there are several flavours of

From: Andrew Trick [mailto:atrick at apple.com] Sent: 24 January 2014 21:52 To: Daniel Sanders Cc: LLVM Developers Mailing List (llvmdev at cs.uiuc.edu) Subject: Re: New machine model questions On Jan 24, 2014, at 2:21 AM, Daniel Sanders <Daniel.Sanders at imgtec.com<mailto:Daniel.Sanders at imgtec.com>> wrote: Hi Andrew, I seem to be making good progress on the P5600 scheduler

On Mar 4, 2014, at 10:05 AM, Pete Cooper <peter_cooper at apple.com> wrote: > > On Mar 3, 2014, at 2:21 PM, Andrew Trick <atrick at apple.com> wrote: > >> >> On Mar 3, 2014, at 8:53 AM, Pierre-Andre Saulais <pierre-andre at codeplay.com> wrote: >> >>> Hi Andrew, >>> >>> We are currently using a custom model where

Hi Jakob, thanks for the advice. I'll do as you suggest and make sure that CCR is never live. I can use pseudo-instructions to bundle cmp+jump but it's not ideal because I might also have to bundle cmp+jump+jump+... into a pseudo. Also, there are several flavours of cmp instruction so I might need a lot of pseudos. That's what led me to wonder whether MachineInstrBundles might be a

On Mar 3, 2014, at 8:53 AM, Pierre-Andre Saulais <pierre-andre at codeplay.com> wrote: > Hi Andrew, > > We are currently using a custom model where scheduling information is attached to each MCInstrDesc through tablegen, and we're trying to move to one of LLVM's models. > > To expand on what JinGu mentioned, our target has explicit ports that are used to read and

...es this happen after SDNodes are converted to MachineInstrs? It's not clear to me given your description of ScheduleDAGInstrs. I assume it uses the current SDNode->SUnit mechanism but I just want to make sure. > 3. New scheduling algorithms can be introduced by implementing new > MachineSchedStrategies. We can add a target hook to select the > strategy if needed. This sounds like what we want and yes, it should be target-selectable. > There's still plenty of opportunity to restructure the code and add > customization points. Keep in mind that the goal for the target > inde...

Sent from my iPhone On Jun 28, 2013, at 2:38 PM, Ghassan Shobaki <ghassan_shobaki at yahoo.com> wrote: > Hi, > > We are currently in the process of upgrading from LLVM 2.9 to LLVM 3.3. We are working on instruction scheduling (mainly for register pressure reduction). I have been following the llvmdev mailing list and have learned that a machine instruction (MI) scheduler has been

Hi, We are currently in the process of upgrading from LLVM 2.9 to LLVM 3.3. We are working on instruction scheduling (mainly for register pressure reduction). I have been following the llvmdev mailing list and have learned that a machine instruction (MI) scheduler has been implemented to replace (or work with?) the selection DAG (SD) scheduler. However, I could not find any document that

Thank you for the answers! We are currently trying to test the MI scheduler. We are using LLVM 3.3 with Dragon Egg 3.3 on an x86-64 machine. So far, we have run one SPEC CPU2006 test with the MI scheduler enabled using the option -fplugin-arg-dragonegg-llvm-option='-enable-misched:true' with -O3. This enables the machine scheduler in addition to the SD scheduler. We have verified this by

On Feb 19, 2014, at 1:54 PM, jingu <jingu at codeplay.com> wrote: > Hi Andy, > > I am trying to schedule and packetize instructions for VLIW at post-RA > stage or final codegen stage, where code transformations are not allowed > any more, because hardware can not resolve resource conflict. There is a > simple example as following: > > ADD dest_reg1, src_reg1,

On Jul 2, 2013, at 2:35 PM, Ghassan Shobaki <ghassan_shobaki at yahoo.com> wrote: > Thank you for the answers! We are currently trying to test the MI scheduler. We are using LLVM 3.3 with Dragon Egg 3.3 on an x86-64 machine. So far, we have run one SPEC CPU2006 test with the MI scheduler enabled using the option -fplugin-arg-dragonegg-llvm-option='-enable-misched:true' with -O3.