search for: costmodelanalysi

Hi All, I wanted to do some basic cost estimation of Instruction/BB. There're CostModelAnalysis and CodeMetrics available in 3.1 and 3.2 releases. I've been using 3.0 for a while. I'm wondering whether similar analysis can be done in the old 3.0 release, e.g. back porting the implementation. Thank you! Best, Ryan -------------- next part -------------- An HTML attachment was scrubb...

...t-specific optimization passes) may use TTI and the cost model. Higher-level canonicalization passes should not use it. Thanks, Nadav On Feb 6, 2013, at 1:26 AM, ryan <stdstack at gmail.com> wrote: > Hi All, > I wanted to do some basic cost estimation of Instruction/BB. There're CostModelAnalysis and CodeMetrics available in 3.1 and 3.2 releases. > I've been using 3.0 for a while. I'm wondering whether similar analysis can be done in the old 3.0 release, e.g. back porting the implementation. > > Thank you! > > Best, > Ryan > _________________________________...

On Feb 7, 2013, at 3:17 PM, ryan <stdstack at gmail.com> wrote: > Thanks a lot for the reply, Nadav! > I see that using the cost model in target-independent analysis is not good. But I really like the idea of having instruction > cost estimation available. Also the reason I can't directly move to 3.2 code base is that it fails to compile(produce bc files) big > project

...d the cost model. Higher-level canonicalization > passes should not use it. > > Thanks, > Nadav > > On Feb 6, 2013, at 1:26 AM, ryan <stdstack at gmail.com> wrote: > > > Hi All, > > I wanted to do some basic cost estimation of Instruction/BB. There're > CostModelAnalysis and CodeMetrics available in 3.1 and 3.2 releases. > > I've been using 3.0 for a while. I'm wondering whether similar analysis > can be done in the old 3.0 release, e.g. back porting the implementation. > > > > Thank you! > > > > Best, > > Ryan > &...

On Thu, Feb 07, 2013 at 04:07:38PM -0800, ryan wrote: > On Thu, Feb 7, 2013 at 3:23 PM, Nadav Rotem <nrotem at apple.com> wrote: > > > > > On Feb 7, 2013, at 3:17 PM, ryan <stdstack at gmail.com> wrote: > > > > > Thanks a lot for the reply, Nadav! > > > I see that using the cost model in target-independent analysis is not > > good. But I

On Thu, Feb 7, 2013 at 3:23 PM, Nadav Rotem <nrotem at apple.com> wrote: > > On Feb 7, 2013, at 3:17 PM, ryan <stdstack at gmail.com> wrote: > > > Thanks a lot for the reply, Nadav! > > I see that using the cost model in target-independent analysis is not > good. But I really like the idea of having instruction > > cost estimation available. Also the

There is CostModel.cpp since LLVM3, I am wondering if anyone can give me an concrete example on how to use this pass to estimate cycles used in a given IR file. Thank you very much. Don

Hi, Does LLVM define some performance model for each type of instructions? I mean the cost or latency for executing each type of instruction. Thanks a lot! Best, Linhai

...able would be very time consuming. I studied tets case suggest by you on phabricator, for RegUsageInfo passes I am thinking to print clobbered registers and verify that with FileCheck as expected clobbered register for a particular test-case. Is this approach fine? I did not find function call to CostModelAnalysis::print() , Is opt -analyze making that call ? I am not able to find similar option in llc. I can't use info printed with dbgs() function as release build do not add -debug-only option to llc executable. For the testcase sent by you earlier I have modified it as following : ;;;;; ip-regallco-s...

...; I studied tets case suggest by you on phabricator, for RegUsageInfo > passes I am thinking to print clobbered registers and verify that with > FileCheck as expected clobbered register for a particular test-case. Is > this approach fine? > > > > I did not find function call to CostModelAnalysis::print() , Is opt > -analyze making that call ? > > Yes. > (In general, if you find yourself in a situation where you can find the > caller for a function, run in a debugger and set a breakpoint) > Ok > > > I am not able to find similar option in llc. > > That'...

...e suggest by you on phabricator, for RegUsageInfo >> passes I am thinking to print clobbered registers and verify that with >> FileCheck as expected clobbered register for a particular test-case. Is >> this approach fine? >> > >> > I did not find function call to CostModelAnalysis::print() , Is opt >> -analyze making that call ? >> >> Yes. >> (In general, if you find yourself in a situation where you can find the >> caller for a function, run in a debugger and set a breakpoint) >> > Ok > >> >> > I am not able to find...

Dear Mentors, I will be writing test cases for IPRA for lit infrastructure. Following 2 basic test cases I have identified : Program that does not have recursive function call. Program that does have recursive calls. Please suggest some other test cases or provide some hints. Sincerely, Vivek -------------- next part -------------- An HTML attachment was scrubbed... URL: