catch python buffer unsupported types

[shivadbhavsar]

Issue:
New datatypes (fp8 and bf16) are not natively supported by the python buffer protocol. See https://docs.python.org/3/library/struct.html#format-characters

This can lead to some silly behavior since all unsupported types seem to give format string "z". Example:

import migraphx
p = migraphx.program()
mm = p.get_main_module()
s = migraphx.shape(type="bf16_type", lens=[16])
a = migraphx.generate_argument(s) 
l = mm.add_literal(a)
print(a.get_shape()) # bf16_type, {16}, {1}
print(l.shape()) # fp8e5m2fnuz_type, {16}, {2} ??????????

Fix:

1. explicitly error out if the python buffer format string is "z".
2. add add_literal_from_argument method that allows the user to directly add an argument to some module they may or may not be a recognized type by py buffer protocol.

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 1 line in your changes missing coverage. Please review.

Project coverage is 92.23%. Comparing base (2e59073) to head (9053020).

Files with missing lines	Patch %	Lines
src/module.cpp	0.00%	1 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #3701   +/-   ##
========================================
  Coverage    92.23%   92.23%           
========================================
  Files          514      514           
  Lines        21746    21746           
========================================
  Hits         20057    20057           
  Misses        1689     1689           

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

[migraphx-bot]

Test	Batch	Rate new 905302	Rate old 64fe0c	Diff	Compare
torchvision-resnet50	64	3,256.98	3,254.94	0.06%	✅
torchvision-resnet50_fp16	64	6,988.80	6,977.96	0.16%	✅
torchvision-densenet121	32	2,435.96	2,436.55	-0.02%	✅
torchvision-densenet121_fp16	32	4,047.38	4,076.26	-0.71%	✅
torchvision-inceptionv3	32	1,628.13	1,627.46	0.04%	✅
torchvision-inceptionv3_fp16	32	2,742.76	2,741.58	0.04%	✅
cadene-inceptionv4	16	764.62	764.31	0.04%	✅
cadene-resnext64x4	16	812.65	813.14	-0.06%	✅
slim-mobilenet	64	7,455.82	7,466.83	-0.15%	✅
slim-nasnetalarge	64	209.05	209.03	0.01%	✅
slim-resnet50v2	64	3,440.47	3,443.32	-0.08%	✅
bert-mrpc-onnx	8	1,143.33	1,144.17	-0.07%	✅
bert-mrpc-tf	1	477.19	474.21	0.63%	✅
pytorch-examples-wlang-gru	1	428.28	416.53	2.82%	✅
pytorch-examples-wlang-lstm	1	392.94	384.23	2.27%	✅
torchvision-resnet50_1	1	812.98	783.29	3.79%	🔆
cadene-dpn92_1	1	400.25	398.94	0.33%	✅
cadene-resnext101_1	1	382.55	383.46	-0.24%	✅
onnx-taau-downsample	1	345.37	345.52	-0.04%	✅
dlrm-criteoterabyte	1	33.35	33.33	0.08%	✅
dlrm-criteoterabyte_fp16	1	52.72	52.73	-0.02%	✅
agentmodel	1	8,083.36	8,127.83	-0.55%	✅
unet_fp16	2	58.95	58.89	0.10%	✅
resnet50v1_fp16	1	908.92	938.63	-3.17%	🔴
resnet50v1_int8	1	989.67	984.73	0.50%	✅
bert_base_cased_fp16	64	1,170.70	1,170.23	0.04%	✅
bert_large_uncased_fp16	32	362.77	362.94	-0.05%	✅
bert_large_fp16	1	200.22	200.28	-0.03%	✅
distilgpt2_fp16	16	2,200.08	2,198.50	0.07%	✅
yolov5s	1	534.63	531.33	0.62%	✅
tinyllama	1	43.35	43.34	0.03%	✅
vicuna-fastchat	1	172.69	172.03	0.38%	✅
whisper-tiny-encoder	1	417.68	418.00	-0.08%	✅
whisper-tiny-decoder	1	429.22	428.83	0.09%	✅

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