search for: widenings

Hi all, I'm working on a target whose registers have equal-sized subregisters and all of those subregisters can be named (or the other way round: registers can be grouped into super registers). So for instance we've got 16 registers W (as in wide) W0..W15 and 32 registers N (as in narrow) N0..N31. This way, W0 is made by grouping N0 and N1, W1 is N2 and N3, W2 is N4 and N5, ..., W15 is

________________________________ From: Kostya Serebryany [kcc at google.com] Sent: Wednesday, December 28, 2011 2:46 PM To: Criswell, John T Cc: llvmdev at cs.uiuc.edu Subject: Re: [LLVMdev] load widening conflicts with AddressSanitizer On Wed, Dec 28, 2011 at 12:40 PM, Criswell, John T <criswell at illinois.edu<mailto:criswell at illinois.edu>> wrote: Dear All, I think adding

Dear All, I think adding metadata and expecting transforms to repect it is a bad idea. It is just too easy for someone who does not know about the metadata to add a transform that ignores it. As for SAFECode, I think we have one of several options for handling load-widening. The most obvious one is to have a pass that just boosts the allocation size of any alloca with an align 16 attribute;

Hi, [resurrecting an old mail thread about AddressSanitizer false positive caused by load widening] Once the Attribute::AddressSafety is set by clang (a separate patch), fixing this bug may look as simple as this: --- lib/Analysis/MemoryDependenceAnalysis.cpp (revision 148708) +++ lib/Analysis/MemoryDependenceAnalysis.cpp (working copy) @@ -323,6 +323,14 @@

On Wed, Dec 28, 2011 at 12:40 PM, Criswell, John T <criswell at illinois.edu>wrote: > Dear All, > > I think adding metadata and expecting transforms to repect it is a bad > idea. It is just too easy for someone who does not know about the metadata > to add a transform that ignores it. > > As for SAFECode, I think we have one of several options for handling >

Hi, I noticed a significant performance regression (up to 40%) on some internal CUDA benchmarks (a reduced example presented below). The root cause of this regression seems that IndVarSimpilfy widens induction variables assuming arithmetics on wider integer types are as cheap as those on narrower ones. However, this assumption is wrong at least for the NVPTX64 target. Although the NVPTX64 target

Hi Nadav, I believe the implementation to keep on widening the vector to the next power of two must be in TargetLowering.h because that is where we decide whether to Widen the vector or not, and the size to which we widen it. In this case, we stop at 4xi8 and do not check if it is legal or not. But the comment says ‘try to widen vector elements until a legal type is found’. Also, there is a

Currently, the GVN optimization widens loads if the alignment permits it. There are some limitations that show up, as seen in example below: Initial IR: declare void @consume(i8) readonly define i8 @bar(i8* align 2 %a) { %1 = load i8, i8* %a %idx = getelementptr i8, i8* %a, i64 1 %2 = load i8, i8* %idx, align 1 call void @consume(i8 %1). ret i8 %2 } define i1 @foo(i8* %a) { entry:

Hi Quentin, > It sounds like you only need the earlyclobber description for the N, N > variant. > In other words, as long as you use different opcodes for widen-op NN and > widen-op WN, you model exactly what you want. > > What am I missing? > we are using different opcodes for widen-op NN and widen-op WN. My understanding is that not setting earlyclobber to the W, N

On Fri, Dec 16, 2011 at 6:08 PM, Kostya Serebryany <kcc at google.com> wrote: > In this case, we have an array of 22 bytes which is 16-aligned. >> I suspect that load widening changed the alignment of alloca instruction >> to make the transformation legal. Right? >> Can we change the load widening algorithm to also change the size of >> alloca instruction to be

----- Original Message ----- > From: "Nadav Rotem" <nrotem at apple.com> > To: "Hal Finkel" <hfinkel at anl.gov> > Cc: "llvmdev at cs.uiuc.edu Dev" <llvmdev at cs.uiuc.edu> > Sent: Wednesday, March 6, 2013 3:40:50 PM > Subject: Re: [LLVMdev] Vector splitting vs widening > > Hi Hal, > > > > > > > The

Hello, My input language has support for 3 and 4 element vectors but my target only has support for the latter. The language defines vec3 with the same storage space as vec4 so from a backend perspective they are both the same. I'd really like if I could have LLVM treat vec3 as vec4 but I haven't found out how. Currently the target has emulated support for vec3 through LLVM. Loads are

On Dec 16, 2011, at 2:27 PM, Kostya Serebryany wrote: > This is a good question. Would it be possible for ASan to do its instrumentation earlier? > > It would be possible but undesirable. > First, asan blows up the IR and running asan early will increase the compile-time. > Second, asan greatly benefits from all optimizations running before it because it needs to instrument

On Fri, Dec 16, 2011 at 2:35 PM, Chris Lattner <clattner at apple.com> wrote: > On Dec 16, 2011, at 2:27 PM, Kostya Serebryany wrote: > > This is a good question. Would it be possible for ASan to do its >> instrumentation earlier? >> > > It would be possible but undesirable. > First, asan blows up the IR and running asan early will increase the >

Ok, thanks. Are there any plans to reintroduce it on the IR level? I'm not confident this is strictly necessary, but in some cases not having load widening ends up really bad. Like in the case where vectorizer tries to do something about it: https://godbolt.org/z/60RuEw https://bugs.llvm.org/show_bug.cgi?id=42708 At the current state I'm forced to use memset() to express uint64 load from

Hi, Can I ask what is the status of load widening. It seems there is no load widening on IR at all. // Paweł On Wed, Oct 5, 2016 at 1:49 PM Artur Pilipenko via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Philip and I talked about this is person. Given the fact that load > widening in presence of atomics is irreversible transformation we agreed > that we don't want to do

One of the arguments for doing this earlier is inline cost perception of the original pattern. Reading i32/i64 by bytes look much more expensive than it is and can prevent inlining of interesting function. Inhibiting other optimizations concern can be addressed by careful selection of the pattern we’d like to match. I limit the transformation to the case when all the individual have no uses other

Hi Nadav, On 2013-08-12 12:59 PM, "Nadav Rotem" <nrotem at apple.com> wrote: >Hi Paul, > >You can read about it here: >http://blog.llvm.org/2011/12/llvm-31-vector-changes.html > >> Hi, >> >> I am trying to understand how vector type legalization works. In >>particular, I'm looking at i8 vector types on x86 (with sse42 features)

Hello, Working on my (currently out-of-tree) BG/Q PPC enhancements, I've run into the following problem with vector type legalization. Here's a quick example: Scalarize node result 0: 0x2348420: v1f32 = extract_subvector 0x23434a0, 0x2348320 [ID=0] Scalarize node result 0: 0x2348220: v1f32 = extract_subvector 0x23434a0, 0x23466e0 [ID=0] Split node result: 0x23469e0: v4f32 =

James, Thanks for your response. I'm working in LLVM 2.7 (I know, it's old) and the default behavior is already promote. This means that for example a call to DAGTypeLegalizer::getTypeAction(v3i32) in my case and I presume in ARM NEON returns TypeWidenVector. From here legalization calls WidenVectorOperand() to process the STORE node and follows the call chain I have on my original email