Build with ubuntu 22.04 in the dockerfiles

[pfultz2]

No description provided.

[codecov]

Codecov Report

Merging #2017 (98ec8a0) into develop (d2486dc) will increase coverage by 0.05%.
Report is 21 commits behind head on develop.
The diff coverage is 99.40%.

❗ Current head 98ec8a0 differs from pull request most recent head b867566. Consider uploading reports for the commit b867566 to get more accurate results

@@             Coverage Diff             @@
##           develop    #2017      +/-   ##
===========================================
+ Coverage    91.43%   91.49%   +0.05%     
===========================================
  Files          422      424       +2     
  Lines        15771    15881     +110     
===========================================
+ Hits         14420    14530     +110     
  Misses        1351     1351              

Files Changed	Coverage Δ
src/include/migraphx/matcher.hpp	97.14% <ø> (ø)
src/include/migraphx/op/contiguous.hpp	100.00% <ø> (ø)
src/include/migraphx/op/scatter.hpp	100.00% <ø> (ø)
src/include/migraphx/shape.hpp	88.88% <ø> (ø)
src/include/migraphx/simplify_reshapes.hpp	100.00% <ø> (ø)
src/targets/ref/lowering.cpp	96.90% <ø> (ø)
src/common_dims.cpp	98.33% <98.33%> (ø)
src/fuse_pointwise.cpp	98.41% <100.00%> (+0.54%)	⬆️
src/include/migraphx/check_shapes.hpp	95.06% <100.00%> (+1.91%)	⬆️
src/include/migraphx/common_dims.hpp	100.00% <100.00%> (ø)
... and 17 more

[migraphx-bot]

Test	Batch	Rate new 79bff0	Rate old 88cf1c	Diff	Compare
torchvision-resnet50	64	2,852.37	2,849.48	0.10%	✅
torchvision-resnet50_fp16	64	6,516.67	6,514.84	0.03%	✅
torchvision-densenet121	32	2,093.49	2,078.58	0.72%	✅
torchvision-densenet121_fp16	32	3,694.35	3,692.57	0.05%	✅
torchvision-inceptionv3	32	1,604.16	1,602.28	0.12%	✅
torchvision-inceptionv3_fp16	32	2,574.56	2,572.10	0.10%	✅
cadene-inceptionv4	16	724.97	724.23	0.10%	✅
cadene-resnext64x4	16	682.95	682.06	0.13%	✅
slim-mobilenet	64	5,946.68	5,933.78	0.22%	✅
slim-nasnetalarge	64	153.72	153.55	0.11%	✅
slim-resnet50v2	64	2,668.22	2,666.28	0.07%	✅
bert-mrpc-onnx	8	825.80	826.20	-0.05%	✅
bert-mrpc-tf	1	380.63	382.76	-0.56%	✅
pytorch-examples-wlang-gru	1	232.64	237.86	-2.19%	✅
pytorch-examples-wlang-lstm	1	244.39	242.19	0.90%	✅
torchvision-resnet50_1	1	613.98	609.59	0.72%	✅
cadene-dpn92_1	1	392.32	391.40	0.24%	✅
cadene-resnext101_1	1	332.22	331.97	0.07%	✅
onnx-taau-downsample	1	305.49	305.35	0.04%	✅
dlrm-criteoterabyte	1	21.61	21.59	0.11%	✅
dlrm-criteoterabyte_fp16	1	40.70	40.59	0.28%	✅
agentmodel	1	4,690.76	3,256.76	44.03%	🔆
unet_fp16	2	56.18	nan	nan%	❌
resnet50v1_fp16	1	875.14	nan	nan%	❌
resnet50v1_int8	1	787.50	nan	nan%	❌
bert_base_cased_fp16	64	936.39	nan	nan%	❌
bert_large_uncased_fp16	32	292.67	nan	nan%	❌
bert_large_fp16	1	184.68	nan	nan%	❌
distilgpt2_fp16	16	1,638.11	nan	nan%	❌
yolov5s	1	498.26	nan	nan%	❌
tinyllama	1	32.65	nan	nan%	❌
vicuna-fastchat	1	155.07	nan	nan%	❌
whisper-tiny-encoder	1	334.97	nan	nan%	❌
whisper-tiny-decoder	1	373.91	nan	nan%	❌

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     ✅ bert-mrpc-tf: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

     ✅ unet: PASSED: MIGraphX meets tolerance

     ✅ resnet50v1: PASSED: MIGraphX meets tolerance

     ✅ bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

     ✅ bert_large: PASSED: MIGraphX meets tolerance

     ✅ yolov5s: PASSED: MIGraphX meets tolerance

     ✅ tinyllama: PASSED: MIGraphX meets tolerance

     ✅ vicuna-fastchat: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 91.64%. Comparing base (0c3f2ca) to head (79bff0c).

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #2017   +/-   ##
========================================
  Coverage    91.64%   91.64%           
========================================
  Files          472      472           
  Lines        17848    17848           
========================================
  Hits         16357    16357           
  Misses        1491     1491           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[pfultz2]

So MLIR fails to build on 22.04:

Traceback (most recent call last):
  File "/usr/local/cget/build/tmp-25313f4698354e8987318405eb382ca9/rocMLIR-bf2911e5245d6452d194ee5dc41c9c2b2869e5c0/external/llvm-project/mlir/lib/Dialect/GPU/AmdDeviceLibsIncGen.py", line 53, in <module>
    generate(Path(sys.argv[1]), Path(sys.argv[2]), sys.argv[3:])
  File "/usr/local/cget/build/tmp-25313f4698354e8987318405eb382ca9/rocMLIR-bf2911e5245d6452d194ee5dc41c9c2b2869e5c0/external/llvm-project/mlir/lib/Dialect/GPU/AmdDeviceLibsIncGen.py", line 29, in generate
    with (bcPath / (lib + ".bc")).open("rb") as libFile:
  File "/usr/lib/python3.10/pathlib.py", line 1119, in open
    return self._accessor.open(self, mode, buffering, encoding, errors,
FileNotFoundError: [Errno 2] No such file or directory: '/usr/amdgcn/bitcode/ocml.bc'

[pfultz2]

I opened this issue:

ROCm/rocMLIR#1415

[pfultz2]

So I was missing a pin for the hip-clang docker. It should be fixed now.

[pfultz2]

@causten This passes the CI, so I think this can be reviewed and merged.