CuAssembler

CuAssembler copied to clipboard

Errors on CUDA 11.6

1

Hi, I tried to use CuAssembler on the sample CuTest code. It works well on the build-in cubin files. However, when I recompiled it using NVCC11.6 and the same arguments,...

wpybtw

Error when assembling instruction "[B------:R3:W4:-:S06] @P3 LDG.E.EL.128 R12, desc[UR8][R16.64] ;":

2

Hi, Many thanks for releasing this assembler! I was trying to disassemble pytorch's kernel, but and then I saw this error: Error when assembling instruction "[B------:R3:W4:-:S06] @P3 LDG.E.EL.128 R12, desc[UR8][R16.64]...

hgl71964

about the "L2::128B"

1

Hi, big god I meet a new trouble about "LDG"，the assembler raise exception like this: ` File hack.main.sm_86.cuasm:795 : [B------:R-:W2:-:S04] /*0080*/ LDG.E.LTC128B.CONSTANT R4, desc[UR4][R2.64] ; Error when assembling instruction "[B------:R-:W2:-:S04]...

Shaquille-Wu

how to understand "L2Bank"

1

Hi, big god. I found the "L2Bank" in your microbenchmark. I don't know the principle and theory of your code. would you like to teach me? I found some reference...

Shaquille-Wu

Can we eliminate all negative numbers in the weight matrixs？

3

I found that there are many negative numbers in the weight matrixs. From what I see， this is because a certain modifier is omitted for some instruction . Such as...

gongxiaozhang

Assembling failed (NewModi): Unknown modifiers: ({'2_R.64'})

7

mhi, big god my CuAssembler raise exception when I test the "TestData" my nvcc is 11.3, and my arch is sm_86 it throw following exception when I executed "make hack":...

Shaquille-Wu

raise Exception('Unknown implicit section %s !'%secname)

4

C:\Python39>python "G:\CuAssembler\bin\cuasm.py" --bin2asm "G:\elf3.dat" ,023 - - Running CubinFile.loadCubin... ,023 - ENTRY - Loading cubin file G:\elf3.dat... ,044 - - Running CubinFile.disassembleCubin... ,044 - PROC - Disassembling G:\elf3.dat... ,779 -...

KurapicaBS

make dump issue

6

Hello, When I try cuassember followed your suggestion , I run 'make dump' but I met next issue , could you kindly help ? HNVCC_OP=dump hnvcc test_war.cu -arch=sm_60 -o test_war...

eric1hello

Exception: ('Duplicate symbol @%#x with name %s!', 24, '')

2

[libcublasLt_static.1028.sm_75.zip](https://github.com/cloudcores/CuAssembler/files/10520023/libcublasLt_static.1028.sm_75.zip) [libcublasLt_static.1028.sm_75_cubin.zip](https://github.com/cloudcores/CuAssembler/files/10520032/libcublasLt_static.1028.sm_75_cubin.zip) I successfully create the assembly code from libcublasLt_static.1028.sm_75.cubin with cuasm libcublasLt_static.1028.sm_75.cubin. When I try to regenerate the cubin with cuasm libcublasLt_static.1028.sm_75.cuasm -o new_libcublasLt_static.1028.sm_75.cubin it shows me the following...

manospavlidakis

About Ada (fp8 tensor core) and tensor core mma (and mma.sp) support..

2

Hi, Just want to know status on tensor core support.. Thanks..

oscarbg