JanLJL
97756faa04
Merge branch 'master' into pr-armcc
2023-03-14 17:50:48 +01:00
JanLJL
0985e81b23
added more dependency analysis for post/pre indexing and condition flags
2023-03-14 17:00:02 +01:00
JanLJL
c1373fe44c
enabled indexing without shape and lane for vector regs
2023-03-03 14:41:48 +01:00
Décio Luiz Gazzoni Filho
b434e30ec1
Support for flags and conditional ops on AArch64
2023-02-19 22:08:42 -03:00
JanLJL
9bbb289f9d
formatting
2022-04-07 12:17:08 +02:00
Qingcai Jiang
728bb03a93
fix a bug about orr in tsv110
2022-03-20 14:53:34 +08:00
Jan
b18f7bf718
black-conform formatting
2021-12-03 14:38:52 +01:00
Qingcai Jiang
3efda4ba6c
fix a bug when the hex_number of address is negative
2021-12-03 15:13:54 +08:00
JanLJL
3404d72dc5
enhanced parser
2021-09-29 17:26:27 +02:00
JanLJL
1b40c10a1f
applied flake8 and black rules
2021-08-26 16:58:19 +02:00
JanLJL
ec771dbe91
fixed parsing of reg ranges and lists
2021-06-01 00:10:05 +02:00
JanLJL
5038ce7a15
changed immediate type from str to int
2021-05-10 01:12:30 +02:00
JanLJL
30d6f4d737
fix #73
2021-05-02 22:22:30 +02:00
Julian Hammer
781b8b6b89
improved register range and list support on AArch64
2021-04-23 13:12:18 +02:00
Julian
04836cf3f9
Validation ( #71 )
...
Validating of OSACA predictions for IVB, SKX, ZEN1, ZEN2, A64FX and TX2 with different kernels.
build_and_run.py contains the configuration used at RRZE's testcluster and UR's qpace4, Analysis.ipynb contains the analysis script and results. Raw data from measurements (122MB) will be attached to next OSACA release.
For now, find the raw data here: https://hawo.net/~sijuhamm/d/UPIhBOtz/validation-data.tar.gz
The analysis report can be viewed at https://nbviewer.jupyter.org/github/RRZE-HPC/OSACA/blob/validation/validation/Analysis.ipynb
Quite a few changes on OSACA included:
Feature: register change tracking via semantic understanding of operations
Feature: recording LCD latency along path and exposing this to frontend
Feature: support for memory reference aliases
Feature: store throughput scaling (similar to load throughput scaling)
Fix: model importer works with latest uops.info export
Fix: immediate type tracking on ARM now preserves type in internal representaion
Removed unused KerncraftAPI
2021-04-15 14:42:37 +02:00
Julian Hammer
afa607e546
migrate code style to Black
2021-03-11 12:02:45 +01:00
Julian Hammer
c788e7b97b
passing parsing errors to the outside
2021-03-05 18:07:36 +01:00
JanLJL
70ddce85c9
fixed AArch64 parser for register shifts and new instructions for A64FX
2021-02-25 07:43:42 +01:00
Jan
ffcdee5ed9
suppress branch indication in mnemonic for now
2021-01-07 10:20:57 +01:00
jdomke
eb1a8a2674
att parser: support for more mnemonic
...
found some 'jg,pt' in icc/mkl generated binaries which crashed the
parser, here an example:
dd8ccd: 3e 7f 90 jg,pt dd8c60 <mkl_blas_avx2_dtrsm_kernel...
2021-01-05 15:26:22 +09:00
JanLJL
7b83e4a370
fixes #61
2020-12-28 10:33:54 +01:00
JanLJL
407c1a2beb
add support for :: delimiter in x86 labels and identifiers
2020-12-07 02:45:49 +01:00
JanLJL
9a6866417e
added support for absolute address operands without brackets
2020-12-07 01:57:06 +01:00
JanLJL
c783b2ce2d
enhancements for lookup and parsing AArch64 instrs
2020-12-07 01:18:32 +01:00
JanLJL
40afe51454
added the possibility of a 5th operand
2020-12-06 18:05:59 +01:00
JanLJL
0ca6e12e87
bugfixes
2020-11-21 21:00:58 +01:00
JanLJL
e643520a79
replaced 582b46b3 with smarter solution
2020-11-20 15:44:49 +01:00
JanLJL
582b46b347
bugfix for immediate shifts with hex-base
2020-11-20 15:22:05 +01:00
JanLJL
6b0673d012
bugfixes
2020-11-09 23:29:42 +01:00
Julian Hammer
7f8b596fc9
improved performance of arch_semantics and reg dependency matching
2020-11-09 19:27:47 +01:00
Julian Hammer
0e4d5a6692
singelton for isa parsers
2020-11-09 12:36:14 +01:00
JanLJL
aa6252f270
bugfixes
2020-11-06 12:03:54 +01:00
JanLJL
36cf3be579
try different ISA as fallback when parsing without --arch flag, use SKX as x86 default and enhanced ISA detection heuristic
2020-11-02 15:33:50 +01:00
JanLJL
bfd07a83a4
autodetect ISA and default uarch for ISA
2020-10-29 13:00:02 +01:00
JanLJL
22e36f4870
enhanced hanlding for immediates with shifting
2020-10-21 12:14:21 +02:00
JanLJL
537772e223
refactored operand checking in post-processing
2020-10-16 10:05:08 +02:00
JanLJL
2df4b353ed
no \t replacement before any other point than user output
2020-10-16 09:44:18 +02:00
JanLJL
633e93ee4b
Merge branch 'master' into A64FX
2020-10-15 22:44:12 +02:00
JanLJL
fb0ba144a5
adjusted tests for AArch64
2020-10-15 17:56:08 +02:00
Julian Hammer
dff2e27199
fixed label identifiers by splitting
2020-10-12 15:39:32 +02:00
Julian Hammer
9627686166
paranthesis now suppored in identifier strings
2020-10-12 15:05:52 +02:00
JanLJL
28cdcab05f
enhancecd ARM identifier to support immediate offsets
2020-09-17 22:12:12 +02:00
JanLJL
3bea6c6add
fixed first character match for symbolic identifiers
2020-08-03 18:30:29 +02:00
Jan
3e8a89ffad
Merge pull request #49 from RRZE-HPC/coherent_label_parsing
...
Coherent label parsing
2020-08-03 18:25:20 +02:00
JanLJL
20d8e2b217
save b/f in numeric identifier as suffix tag
2020-08-03 18:08:29 +02:00
JanLJL
6c1424e2f7
removed unnecessary code
2020-08-03 17:14:58 +02:00
JanLJL
a75405b77b
detects numeric label as label
2020-08-03 16:59:48 +02:00
Julian Hammer
da1d39e8e6
labels may now start with numbers
2020-08-03 15:53:29 +02:00
JanLJL
fa3056f364
minor enhancement for mask parsing
2020-08-03 09:07:45 +02:00
JanLJL
4fe299df2d
enhancements for SVE support
2020-08-03 08:54:59 +02:00
