[TVM Discuss] [Development] How to debug and print out content of IndexExpr?
`LOG(INFO) << oshape;` ? --- [Visit Topic](https://discuss.tvm.ai/t/how-to-debug-and-print-out-content-of-indexexpr/2039/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/be4b2945d3d3846a9f14e6034edca8b17d405c2565f7de1e45e424c1dbcf). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=TFNN8DT0EShj0WGk4xMTRQ2
Re: [dmlc/tvm] [RFC][EXPR] Formalize Integer Arithmetic Analysis (#2588)
@tqchen I guess we cannot know for sure: the performance benefits of memoization may outweigh the possible performance losses due to immutability. What is more important is that pure functions often make things more clear to think about. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2588#issuecomment-478682406
Re: [dmlc/tvm] [RFC][EXPR] Formalize Integer Arithmetic Analysis (#2588)
What I mean is that we can support memoization even if we don’t do the functionally style, as I outlined in the last post -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2588#issuecomment-478683138
[TVM Discuss] [Development] Low efficiency on my own cpu
In any case, I would recommend autotuning first to see if that makes a difference. --- [Visit Topic](https://discuss.tvm.ai/t/low-efficiency-on-my-own-cpu/2030/13) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/f8edfb4e18d743cf3133605e58fba9e4c3050b19bb46d669587a1be97c79fef3). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=oVu3U2qslm_aYwGjL3aTBg2
Re: [dmlc/tvm] [RFC] Register Relay VM design (#2915)
## Summary @tqchen @icemelon9 @jroesch @zhiics @yongwww we discuss in person. Reached the following consensus: 1. Remove `Phi` instruction. Instead extend `If` to write the result to a new register. 2. Reuse the existing value stack as the register file. Have an anchor in the function frame to point to the start of each function's register region. 3. Try to do liveness on Relay AST to reuse the pass manager infrastructure, and to not introduce extra interfaces. Let me know if I miss anything or said something wrong. I'll take out liveness analysis on opcodes from my branch and polish remaining stuff(register VM + linear scan + interfaces). Since we don't have liveness analysis on Relay AST now, I'll simply generate live interval for each register with the full opcodes range, so register allocator can assign unique slot for each register. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/dmlc/tvm/issues/2915#issuecomment-478796098
[TVM Discuss] [Development] ONNX model compilation fails with a model that previously worked
Yesterday I pulled the latest code and installed from source, which went
without problems. After that, I tried to compile an MNIST onnx model as first
test, which failed with the stacktrace below:
The model can be downloaded here: https://we.tl/t-Tghn9o9EQ8 (md5:
9fc8b23aa4f33008360727d2fe1b0823)
```
File "/home/martin/Dev/xyz/src/tvm/compile_model.py", line 90, in
compile_model
graph_json, lib, params = relay.build_module.build(func=relay_func,
target=target, params=params)
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/relay/build_module.py",
line 276, in build
func = optimize(func, target, params)
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/relay/build_module.py",
line 203, in optimize
func = ir_pass.alter_op_layout(func)
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/relay/ir_pass.py",
line 741, in alter_op_layout
return _ir_pass.AlterOpLayout(expr)
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/_ffi/_ctypes/function.py",
line 190, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (8)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xd1c4bd)
[0x7fec5b8d04bd]
[bt] (7)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xba5e0d)
[0x7fec5b759e0d]
[bt] (6)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xba8867)
[0x7fec5b75c867]
[bt] (5)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xba7734)
[0x7fec5b75b734]
[bt] (4)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xd1d4f5)
[0x7fec5b8d14f5]
[bt] (3)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xcf8770)
[0x7fec5b8ac770]
[bt] (2)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xcf3d98)
[0x7fec5b8a7d98]
[bt] (1)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xcf3000)
[0x7fec5b8a7000]
[bt] (0)
/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/libtvm.so(+0xf2f5eb)
[0x7fec5bae35eb]
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/_ffi/_ctypes/function.py",
line 55, in cfun
rv = local_pyfunc(*pyargs)
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/relay/op/nn/_nn.py",
line 134, in alter_op_layout_conv2d
return topi.nn.conv2d_alter_layout(attrs, inputs, tinfos, op)
File
"",
line 2, in conv2d_alter_layout
File
"/home/martin/.local/lib/python3.6/site-packages/tvm-0.6.dev0-py3.6-linux-x86_64.egg/tvm/target.py",
line 356, in dispatch_func
return dispatch_dict[k](*args, **kwargs)
File
"/home/martin/.local/lib/python3.6/site-packages/topi-0.6.dev0-py3.6.egg/topi/x86/conv2d.py",
line 297, in _alter_conv2d_layout
out_channel = attrs.get_int("channels") if F == sym else
attrs.get_int("channels").value
AttributeError: 'NoneType' object has no attribute 'value'
```
---
[Visit
Topic](https://discuss.tvm.ai/t/onnx-model-compilation-fails-with-a-model-that-previously-worked/2081/1)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/email/unsubscribe/e938149c1c888572d6a2d7d9a34acbced9e8dcbecd619cf2fcd1cd964c35ed9d).
Tianqi Chen, UW, Seattle, WA, 98105, United States
http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=yiTJDTqGNCD1kfohoLtYTw2
[TVM Discuss] [Development] ONNX model compilation fails with a model that previously worked
This looks like someone introduced a bug or regression into the alter layout pass, could you open an issue against dmlc master so we can CC the appropriate people to work on this. You can try to turn off the alter-layout optimization if you want to make progress. --- [Visit Topic](https://discuss.tvm.ai/t/onnx-model-compilation-fails-with-a-model-that-previously-worked/2081/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/614d4d01081dc443dedd435eaf6f61aa93a2d301b3554755293b6bc3cf60de5c). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=DYe-iTZsigvUmr6yU1-lqA2
[TVM Discuss] [Development] ONNX model compilation fails with a model that previously worked
Sure, how can I turn off the optimization? I didn't actively enable it. --- [Visit Topic](https://discuss.tvm.ai/t/onnx-model-compilation-fails-with-a-model-that-previously-worked/2081/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/0136ec51c1504bff55659aca92ebf80b5651c9068f6eed59de35ee9d4c1c1a3b). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=93NL4nVjCQyAjbjsCXbt8w2
[TVM Discuss] [Development] ONNX model compilation fails with a model that previously worked
It should be disabled by default, it is set at optimization level 2, so I'm not sure why it is executing. Can you try: ``` with relay.build_module.build_config(opt_level=2): graph_json, lib, params = relay.build_module.build(...) ``` --- [Visit Topic](https://discuss.tvm.ai/t/onnx-model-compilation-fails-with-a-model-that-previously-worked/2081/4) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/3fbfaaff3655c42c6cbfa98c568db139843ae7a8843189ece072fa02394f3632). Tianqi Chen, UW, Seattle, WA, 98105, United States http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=EBY3Ud31BrBpreXCiZhPgA2
