[llvm-dev] instrumenting device code with gpucc

[Yuanfeng Peng via llvm-dev]

Hey Jingyue,

Thanks for being so responsive!  I finally figured out a way to resolve the
issue: all I have to do is to use `-only-needed` when merging the device
bitcodes with llvm-link.

However, since we actually need to instrument the host code as well,  I
encountered another issue when I tried to glue the instrumented host code
and fatbin together.  When I only instrumented the device code, I used the
following cmd to do so:

"/mnt/wtf/tools/bin/clang-3.9" "-cc1" "-triple" "x86_64-unknown-linux-gnu"
"-aux-triple" "nvptx64-nvidia-cuda" "-fcuda-target-overloads"
"-fcuda-disable-target-call-checks" "-emit-obj" "-disable-free"
"-main-file-name" "axpy.cu" "-mrelocation-model" "static" "-mthread-model"
"posix" "-fmath-errno" "-masm-verbose" "-mconstructor-aliases"
"-munwind-tables" "-fuse-init-array" "-target-cpu" "x86-64"
"-momit-leaf-frame-pointer" "-dwarf-column-info" "-debugger-tuning=gdb"
"-resource-dir" "/mnt/wtf/tools/bin/../lib/clang/3.9.0" "-I"
"/usr/local/cuda-7.0/samples/common/inc" "-internal-isystem"
"/usr/lib/gcc/x86_64-linux-gnu/4.8/../../../../include/c++/4.8"
"-internal-isystem"
"/usr/lib/gcc/x86_64-linux-gnu/4.8/../../../../include/x86_64-linux-gnu/c++/4.8"
"-internal-isystem"
"/usr/lib/gcc/x86_64-linux-gnu/4.8/../../../../include/x86_64-linux-gnu/c++/4.8"
"-internal-isystem"
"/usr/lib/gcc/x86_64-linux-gnu/4.8/../../../../include/c++/4.8/backward"
"-internal-isystem" "/usr/local/include" "-internal-isystem"
"/mnt/wtf/tools/bin/../lib/clang/3.9.0/include" "-internal-externc-isystem"
"/usr/include/x86_64-linux-gnu" "-internal-externc-isystem" "/include"
"-internal-externc-isystem" "/usr/include" "-internal-isystem"
"/usr/local/cuda/include" "-include" "__clang_cuda_runtime_wrapper.h" "-O3"
"-fdeprecated-macro" "-fdebug-compilation-dir"
"/mnt/wtf/workspace/cuda/gpu-race-detection" "-ferror-limit" "19"
"-fmessage-length" "291" "-pthread" "-fobjc-runtime=gcc" "-fcxx-exceptions"
"-fexceptions" "-fdiagnostics-show-option" "-vectorize-loops"
"-vectorize-slp" "-o" "axpy-host.o" "-x" "cuda" "tests/axpy.cu"
"-fcuda-include-gpubinary" "axpy-sm_30.fatbin"

which, from my understanding, compiles the host code in tests/axpy.cu and
link it with axpy-sm_30.fatbin.  However, now that I instrumented the IR of
the host code (axpy.bc) and did `llc axpy.bc -o axpy.s`, which cmd should I
use to link axpy.s with axpy-sm_30.fatbin?  I tried to use -cc1as, but the
flag '-fcuda-include-gpubinary' was not recognized.

Thanks!

yuanfeng

On Sat, Mar 12, 2016 at 12:05 AM, Jingyue Wu <jingyue at google.com> wrote:

> I've no idea. Without instrumentation, nvvm_reflect_anchor doesn't appear
> in the final PTX, right? If that's the case, some pass in llc must have
> deleted the anchor and you should be able to figure out which one.
>
> On Fri, Mar 11, 2016 at 4:56 PM, Yuanfeng Peng <
> yuanfeng.jack.peng at gmail.com> wrote:
>
>> Hey Jingyue,
>>
>> Though I tried `opt -nvvm-reflect` on both bc files, the nvvm reflect
>> anchor didn't go away; ptxas is still complaining about the duplicate
>> definition of of function '_ZL21__nvvm_reflect_anchorv' .  Did I misused
>> the nvvm-reflect pass?
>>
>> Thanks!
>> yuanfeng
>>
>> On Fri, Mar 11, 2016 at 10:10 AM, Jingyue Wu <jingyue at google.com> wrote:
>>
>>> According to the examples you sent, I believe the linking issue was
>>> caused by nvvm reflection anchors. I haven't played with that, but I guess
>>> running nvvm-reflect on an IR removes the nvvm reflect anchors. After that,
>>> you can llvm-link the two bc/ll files.
>>>
>>> Another potential issue is that your cuda_hooks-sm_30.ll is unoptimized.
>>> This could cause the instrumented code to run super slow.
>>>
>>> On Fri, Mar 11, 2016 at 9:40 AM, Yuanfeng Peng <
>>> yuanfeng.jack.peng at gmail.com> wrote:
>>>
>>>> Hey Jingyue,
>>>>
>>>> Attached are the .ll files.  Thanks!
>>>>
>>>> yuanfeng
>>>>
>>>> On Fri, Mar 11, 2016 at 3:47 AM, Jingyue Wu <jingyue at google.com> wrote:
>>>>
>>>>> Looks like we are getting closer!
>>>>>
>>>>> On Thu, Mar 10, 2016 at 5:21 PM, Yuanfeng Peng <
>>>>> yuanfeng.jack.peng at gmail.com> wrote:
>>>>>
>>>>>> Hi Jingyue,
>>>>>>
>>>>>> Thank you so much for the helpful response!  I didn't know that PTX
>>>>>> assembly cannot be linked; that's likely the reason for my issue.
>>>>>>
>>>>>> So I did the following as you suggested(axpy-sm_30.bc is the
>>>>>> instrumented bitcode, and cuda_hooks-sm_30.bc contains the hook functions):
>>>>>>
>>>>>> *llvm-link axpy-sm_30.bc cuda_hooks-sm_30.bc  -o inst_axpy-sm_30.bc*
>>>>>>
>>>>>> *llc inst_axpy-sm_30.bc -o axpy-sm_30.s*
>>>>>>
>>>>>> *"/usr/local/cuda/bin/ptxas" "-m64" "-O3" -c "--gpu-name" "sm_30"
>>>>>> "--output-file" axpy-sm_30.o axpy-sm_30.s*
>>>>>>
>>>>>> However, I got the following error from ptxas:
>>>>>>
>>>>>> *ptxas axpy-sm_30.s, line 106; error   : Duplicate definition of
>>>>>> function '_ZL21__nvvm_reflect_anchorv'*
>>>>>>
>>>>>> *ptxas axpy-sm_30.s, line 106; fatal   : Parsing error near '.2':
>>>>>> syntax error*
>>>>>>
>>>>>> *ptxas fatal   : Ptx assembly aborted due to errors*
>>>>>>
>>>>>> Looks like some cuda function definitions are in both bitcode files
>>>>>> which caused duplicate definition... what am I supposed to do to resolve
>>>>>> this issue?
>>>>>>
>>>>> Can you attach axpy-sm_30.ll and cuda_hooks-sm_30.ll? The duplication
>>>>> may be caused by how nvvm reflection works, but I'd like to see a concrete
>>>>> example.
>>>>>
>>>>>>
>>>>>> Thanks!
>>>>>>
>>>>>> yuanfeng
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160313/649db42b/attachment.html>