similar to: Optimization Record

Assume an architecture that has multiple condition code registers, e.g., powerpc. Now assume that there are predicate instructions like thumb2, but can specify which condition code register they refer to. Now also assume that these predicate instructions themselves are predicatible, if executed they change the current predication state. Can LLVM handle multiple levels of predication? When is

Hi, I'm new to llvm and am trying to run benchmarks from the test-suite using lnt to check loop-vectorization for various benchmarks. Test are compiling and executing fine, but I am not getting optimization remarks while using flags like -Rpass-missed=loop-vectorize and -Rpass-analysis=loop-vectorize I've tried running it like this: lnt runtest test-suite --sandbox SANDBOX --cc

I have a global 2-D array ARRAY[N][M] and I am accessing it inside the for loop like this: for (i...) for (j ...) ARRAY[i][j] ... So nothing really weird is happening. If I look at the generated IR, it is also fairly straight forward. @ARRAY0 = dso_local global [32 x [32 x i32]] zeroinitializer, section ".slow_mem", align 32, !dbg !84 ... %45 = getelementptr inbounds [32 x [32 x

Hello all, During the compilation process, LLVM automatically derives various attributes about functions and values (for example that a pointer is nonnull, a function is constant, etc) that are used within a translation unit. I propose adding a pass to LLVM that allows front-ends to output derived attributes. Such a pass would be useful both for developers and end users to debug programs,

Dear LLVM community, How to find out which optimization passes have been performed and which passes have failed? Regards, Pradeep Kumar -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20181117/20c7ad68/attachment.html>

Hi All, I have got one domination error after running LoopVectorizer with VPlanNatviePath. Let's see simple IR snippet after loop vectorization with VPlanNatviePath. vector.body: ... br label %for.body10.preheader67 for.body10.preheader67: ; preds = %for.cond.cleanup972, %vector.body %vec.phi = phi <4 x i64> [ zeroinitializer, %for.cond.cleanup972 ], [ %8,

Hello. I'm trying to understand how fastcall works. As far as I know, first two integer type arguments are passed in ecx and edx. I tested several test, but the result was different from what I expected #1 typedef struct _data_t { int d; } data_t; void __attribute__((fastcall)) test_suuu(data_t s, unsigned int a, unsigned int b, unsigned int c); unsigned int a is passed

Hi, I am trying to compare the loop vectorizers effectiveness for different targets relative to each other. That way, I am hoping to find loops that are not vectorized - but could be - on my target by finding other targets doing this successfully. With some luck, there might be something in the Target files that could be fixed with improved vectorization as a result... I would like to do

Hi guys, I used setMemory in order to dynamically change guest's memory on QEMU-KVM. As expected, memory(total, free, available) in the guest was really changed, but after a few seconds, it automatically reverted to its initial memory. So, setMemory changes the guest's memory temporarily? Thanks.

> On May 11, 2016, at 3:37 AM, Hal Finkel <hfinkel at anl.gov> wrote: > > ----- Original Message ----- >> From: "Adam Nemet" <anemet at apple.com> >> To: "Hal Finkel" <hfinkel at anl.gov> >> Cc: "llvm-dev (llvm-dev at lists.llvm.org)" <llvm-dev at lists.llvm.org> >> Sent: Wednesday, May 11, 2016 1:15:42 AM

Reduction Not Captured By LLVM CODE_1 ------------------------------------------------------------ ------------------------------------------------------------ -------------------- #include <stdio.h> int main() { int sum[1000]={1,2,3,4}; for (int i=1;i<1000;i++) { sum[0] +=sum[i-1]; } }

Hi, I'm using clang frontend. I'm interested in some particular hot loop in my code and I emit a report from vectorizer optimizations passes. I receive nice output if passing -Rpass* flags as long as I'm building without LTO? But with -flto it just prints nothing. Is there a way to emit opt reports when using LTO? For now I can only approximate about whether my the loop will be

This idea came up a few times recently [1][2] so I’d like start prototyping it. To summarize, we can emit optimization remarks using the -Rpass* options. These are currently emitted by optimizations like vectorization[3], unrolling, inlining and since last week loop distribution. For large programs however this can amount to a lot of diagnostics output to sift through. Filtering this by the

Hi Hal, > On May 10, 2016, at 5:39 PM, Hal Finkel <hfinkel at anl.gov> wrote: > > Hi Adam, > > I think would be a really useful feature to have. I don't think that the backend should be responsible for filtering, but should pass the relative hotness information to the frontend. Given that these diagnostics are not just going to be used for -Rpass and friends, but also

Is there any way to find if a optimization pass has passed in opt? In clang -fsave-optimzization-record would tell if particular optimization pass has applied or failed. Is there similar functionality in opt? Regards, Nethish. -------------- next part -------------- An HTML attachment was scrubbed... URL:

Hi llvm-dev! We are doing some fuzzy testing using C program generators, and one question that came up when generating a program with both floating point arithmetic and loop pragmas was; Is the loop vectorizer really allowed to vectorize a loop when it can't prove that it is safe to reorder fp math, even if there is a loop pragma that hints about a preferred width. When reading here

Dear llvm-dev community, I am trying to analyze the optimization remarks generated through clang using -fsave-optimization-remark with -O3. --- !Analysis Pass: loop-vectorize Name: CFGNotUnderstood DebugLoc: { File: c-ray-mt.c, Line: 177, Column: 2 } Function: main Args: - String: 'loop not vectorized: ' - String: loop control flow is not understood by vectorizer I tried to look for

Adam, thanks for all the suggestions! One nice aspect of the `-Rpass` family of options is that I can filter based on what I want. If I only want to see which inlines I missed, I could use `clang -Rpass-missed="inline"`, for example. On the other hand, optimization remark YAML always include remarks from all passes (as far as I can tell), which increases the amount of time it takes

Hi -- I have found a bug in an HPC code where llvm is vectorizing a loop on Skylake that has an obvious recurrence. I derived a small test case based on the original benchmark below: /*****************************************************************/ static void __attribute__ ((always_inline)) one( const int *restrict in, const int *const end, const unsigned shift, int *const restrict index,

Hello, I'm learning how LLVM performs PGO (profile-guided optimizations) by using the instrumentation-based profile build (-fprofile-instr-generate and -fprofile-instr-use). However, I found there is no difference in inlining behaviors between with and without PGO for a few spec benchmarks by checking the emit optimization reports (-Rpass=inline -Rpass-missed=inline -Rpass-analysis=inline).