similar to: Get basic-block cycle cost from LLVM

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 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

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

It it possible to specify an instruction latency in the itinerary through a command line option? We have several options for a hardware divider which have different latencies and it would be nice if I could specify it through a compiler option rather than changing the value in the code and recompiling llvm every time? Any help is appreciated. -- Rail Shafigulin Software Engineer Esencia

----- Original Message ----- > From: "Rail Shafigulin via llvm-dev" <llvm-dev at lists.llvm.org> > To: "llvm-dev" <llvm-dev at lists.llvm.org> > Sent: Monday, November 9, 2015 10:09:07 AM > Subject: Re: [llvm-dev] Is there a way to convert between SchedMachineModel and Itineraries? > > > Anybody? Does anyone at all know how to do it? There is

Is there a way to convert between SchedMachineModel and Itineraries? I was trying to write a very simple VLIW packetizer (Hexagon was my starting point). It turns out that current DFAPacketizer is using itineraries, but my schedule is based on SchedMachineModel (I was recommended to use it since the itineraries are being phased out). I was wondering if there is an automated tool that would

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

> On Nov 9, 2015, at 10:49 AM, Rail Shafigulin <rail at esenciatech.com> wrote: > > On Mon, Nov 9, 2015 at 10:31 AM, Hal Finkel <hfinkel at anl.gov <mailto:hfinkel at anl.gov>> wrote: > ----- Original Message ----- > > From: "Rail Shafigulin via llvm-dev" <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> > > To:

Dear Andrew and the Group, I’m trying come up with a SchedMachineModel for the AMD bulldozer http://en.wikipedia.org/wiki/Bulldozer_(microarchitecture). The model is not exist for the same .Please correct me if am i wrong here. I was going through your reference @ https://llvm.org/svn/llvm-project/llvm/trunk/include/llvm/Target/TargetSchedule.td . But I couldn’t model some of the

Hi, I have a question for my simulation problem: I would like to generate a positive (or semi def positive) covariance matrix, non singular, in wich the spectral decomposition returns me the same values for all dimensions but differs only in eigenvectors. Ex. sigma [,1] [,2] [1,] 5.05 4.95 [2,] 4.95 5.05 > eigen(sigma) $values [1] 10.0 0.1 $vectors [,1]

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

I keep getting this error upon building: > Linking CXX executable ../../bin/opt > ../../lib/libLLVMTarget.so: error: undefined reference to > 'llvm::TargetInstrInfo::getNumMicroOps(llvm::InstrItineraryData > const*, llvm::MachineInstr const*) const' > ../../lib/libLLVMTarget.so: error: undefined reference to >

[I tweaked the subject, #262824 did not introduce the problem, it is just the version I am first seeing this problem] A quick update - I have added 'Sched<[]>' as a base class for all instructions, and also: let hasNoSchedulingInfo = 1; to all the Pseudos, but while most of the errors have gone, I still get the diagnostic for 'COPY' thus: error : No schedule

We'd like to be able to vary the latency of our load instructions based on what address space is being loaded from. I was thinking I could do this by overriding getOperandLatency in our target, but I'm wondering if the addrspace info is available when instructions are scheduled? For example, I have this in our llvm IR: %0 = load i32 addrspace(4)* @answer, align 4 store i32 %0, i32*

Hello all, It seems that it is insufficient to rely on MemorySSA to correctly reorder load/stores. For example, we have this following code: v = load q store 10, p => store 10, p v = load q // This is incorrect if p and q may alias In the MemorySSA representation however, there's no syntactic dependency between load/store, because MemorySSA before transformation would look like this:

Dear R community, I've been writing simple functions for the past year and half and have come across a similar problem several times. The execution of a function within my own function produces NaN's or fails to execute as intended. My conundrum is that I can execute the function outside of my function without error, so it's difficult for me, as a novice functioneer, to figure out

Hello, My out-of-tree target features some high latency instructions (let's call them FXLV). When an FXLV issues, it reserves its destination register and execution continues; if a subsequent instruction attempts to read or write that register, the pipline will stall until the FXLV completes. I have attempted to encode this constraint in the machine scheduler (excerpt at bottom of email).

Hi, I am trying to cross compile code for ARM Cortex m0, m3, and m4. For m0, I use: -target armv6--eabi -mcpu=cortex-m0 That seems to work. For m3 and m4, I use the following which does not work (fatal error: error in backend: CPU: 'cortex-m3' does not support ARM mode): -target armv7m--eabi -mcpu=cortex-m3 and -target armv7em--eabi -mcpu=cortex-m4 Who can help me with the

m0<-epxression((4*theta1*theta2-theta3^2)/(2*x*theta3^2)-0.5*theta1*x) params<-all.vars(m0) this reads all the params from m0 so theta1,2 and 3 correct? params<-params[-which(params=="x")] checks which params are multiplied by x? np<-length(params) for(i in 1:6){ esp<-get(sprintf("m%d",i-1))