openpower-isa.git
2 years agoremove need for explicit-hack for "pcdec." - rc column in minor_4.csv file
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 17:40:33 +0000 (18:40 +0100)]
remove need for explicit-hack for "pcdec." - rc column in minor_4.csv file
can be set "rc=ONE" which tells ISACaller (and PowerDecoder2) to
*always* write to CR0

2 years agolots of really bad hacks, here
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 17:38:34 +0000 (18:38 +0100)]
lots of really bad hacks, here
https://bugs.libre-soc.org/show_bug.cgi?id=933
1) rename to "pcdec." because it always sets CR0. following the convention
   set by "stbcx." etc.
2) hacked ISACaller into submission because this is the first instruction
   supported with "." at the end which is not Rc=1
3) handle_comparison was bypassed when CR0 is detected as explicitly
   an output: there is no point computing Rc=1 EQ/LT/GT/SO when CR0
   is supplied by the pseudocode
4) the test case case_pcdec_simple() was not making explicit deepcopy()
   of the registers, which causes problems
5) various places in actually getting the instruction from the insn
   dictionary, have to special-case "pcdec."
6) sv/trans/svp64.py updated to name "pcdec."
.

2 years agofix/hack some bugs in prefix_codes_cases
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 17:05:48 +0000 (18:05 +0100)]
fix/hack some bugs in prefix_codes_cases

2 years agoadd (sigh) to the hack-job get_pdecode_idx_out2() in ISACaller
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:49:45 +0000 (17:49 +0100)]
add (sigh) to the hack-job get_pdecode_idx_out2() in ISACaller
really should be relying on PowerDecoder2 but hey

2 years agochange variablename dec2.use_svp64_fft to implicit_rs
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:43:31 +0000 (17:43 +0100)]
change variablename dec2.use_svp64_fft to implicit_rs

2 years agoadd match on implicit_rc for pcdec
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:43:13 +0000 (17:43 +0100)]
add match on implicit_rc for pcdec

2 years agorename all "fft" variables in PowerDecoder2 because they are
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:35:16 +0000 (17:35 +0100)]
rename all "fft" variables in PowerDecoder2 because they are
to be used for pcdec as well.
https://bugs.libre-soc.org/show_bug.cgi?id=933

2 years agoadd sv.maddld/mr unit test example with expected results
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:21:00 +0000 (17:21 +0100)]
add sv.maddld/mr unit test example with expected results

2 years agoadd expected results for sv.maddld in openpower/test/mul_cases.py
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 16:12:56 +0000 (17:12 +0100)]
add expected results for sv.maddld in openpower/test/mul_cases.py

2 years agoreduce field name lengths (not in use)
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 10:21:40 +0000 (11:21 +0100)]
reduce field name lengths (not in use)

2 years agowhoops offset-tracking on 3-in 2-out supposed to be by MAXVL not VL
Luke Kenneth Casson Leighton [Fri, 23 Sep 2022 09:13:39 +0000 (10:13 +0100)]
whoops offset-tracking on 3-in 2-out supposed to be by MAXVL not VL

2 years agoremoved unneeded file
Konstantinos Margaritis [Fri, 23 Sep 2022 07:49:56 +0000 (07:49 +0000)]
removed unneeded file

2 years agoupdate Makefile
Konstantinos Margaritis [Fri, 23 Sep 2022 07:33:44 +0000 (07:33 +0000)]
update Makefile

2 years agoadd new SVP64 function
Konstantinos Margaritis [Fri, 23 Sep 2022 07:33:37 +0000 (07:33 +0000)]
add new SVP64 function

2 years agoreduce iterations, taking too long in the simulator
Konstantinos Margaritis [Fri, 23 Sep 2022 07:33:01 +0000 (07:33 +0000)]
reduce iterations, taking too long in the simulator

2 years agorename reference functions with _c suffix, add header
Konstantinos Margaritis [Fri, 23 Sep 2022 07:32:42 +0000 (07:32 +0000)]
rename reference functions with _c suffix, add header

2 years agorenamed variance_svp64.c to variancefuncs_svp64.c
Konstantinos Margaritis [Fri, 23 Sep 2022 07:31:58 +0000 (07:31 +0000)]
renamed variance_svp64.c to variancefuncs_svp64.c

2 years agoadd pcdec -- doesn't yet work due to broken ISACaller RT/RS output handling
Jacob Lifshay [Fri, 23 Sep 2022 03:05:35 +0000 (20:05 -0700)]
add pcdec -- doesn't yet work due to broken ISACaller RT/RS output handling

2 years agofix maddld pseudo-code
Jacob Lifshay [Fri, 23 Sep 2022 03:22:45 +0000 (20:22 -0700)]
fix maddld pseudo-code

2 years agoadd missing minor_4 decoder
Jacob Lifshay [Fri, 23 Sep 2022 03:02:02 +0000 (20:02 -0700)]
add missing minor_4 decoder

2 years agofix 'write reg ' log call
Jacob Lifshay [Fri, 23 Sep 2022 03:00:52 +0000 (20:00 -0700)]
fix 'write reg ' log call

2 years agoadd RC input to isa/caller.py
Jacob Lifshay [Fri, 23 Sep 2022 02:59:40 +0000 (19:59 -0700)]
add RC input to isa/caller.py

2 years agoformat code
Jacob Lifshay [Fri, 23 Sep 2022 02:56:11 +0000 (19:56 -0700)]
format code

2 years agomaddhd[u]/maddld are official ops
Jacob Lifshay [Fri, 23 Sep 2022 01:02:59 +0000 (18:02 -0700)]
maddhd[u]/maddld are official ops

2 years agoformat code
Jacob Lifshay [Fri, 23 Sep 2022 00:37:33 +0000 (17:37 -0700)]
format code

2 years agoadd first (correctly-working) ctr-mode sv.bc test
Luke Kenneth Casson Leighton [Thu, 22 Sep 2022 23:47:26 +0000 (00:47 +0100)]
add first (correctly-working) ctr-mode sv.bc test

2 years agocomment need for waiting on binutils update
Luke Kenneth Casson Leighton [Thu, 22 Sep 2022 12:41:23 +0000 (13:41 +0100)]
comment need for waiting on binutils update

2 years agofix no of iterations in comment, harmless but wrong
Konstantinos Margaritis [Thu, 22 Sep 2022 11:05:34 +0000 (11:05 +0000)]
fix no of iterations in comment, harmless but wrong

2 years agodump memory
Konstantinos Margaritis [Thu, 22 Sep 2022 08:43:46 +0000 (08:43 +0000)]
dump memory

2 years agobetter handling of memory copies, fix vpx_get4x4sse_cs_svp64
Konstantinos Margaritis [Thu, 22 Sep 2022 08:43:26 +0000 (08:43 +0000)]
better handling of memory copies, fix vpx_get4x4sse_cs_svp64

2 years agoremove extra setvl instruction
Konstantinos Margaritis [Thu, 22 Sep 2022 08:42:05 +0000 (08:42 +0000)]
remove extra setvl instruction

2 years agoadd series of double-stride options to test_caller_svp64_dct.py
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 19:49:44 +0000 (20:49 +0100)]
add series of double-stride options to test_caller_svp64_dct.py

2 years agodo not set striding on costables, keep them contiguous.
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 19:17:41 +0000 (20:17 +0100)]
do not set striding on costables, keep them contiguous.
not totally sure this is a good idea, but hey

2 years agogetting better, get rid of the ctr, group src/ref loads
Konstantinos Margaritis [Wed, 21 Sep 2022 18:33:24 +0000 (18:33 +0000)]
getting better, get rid of the ctr, group src/ref loads

2 years agoscale-up svshape pseudo-code for striding in DCT/FFT
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 17:18:14 +0000 (18:18 +0100)]
scale-up svshape pseudo-code for striding in DCT/FFT

2 years agofix dct/fft test-functions with new "scaling" parameter
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 16:56:57 +0000 (17:56 +0100)]
fix dct/fft test-functions with new "scaling" parameter
https://bugs.libre-soc.org/show_bug.cgi?id=930

2 years agomissed setting zdim in svshape on DCT modes
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 14:53:53 +0000 (15:53 +0100)]
missed setting zdim in svshape on DCT modes

2 years agouse sv.subf
Konstantinos Margaritis [Wed, 21 Sep 2022 15:33:49 +0000 (15:33 +0000)]
use sv.subf

2 years agofix braces
Konstantinos Margaritis [Wed, 21 Sep 2022 15:30:45 +0000 (15:30 +0000)]
fix braces

2 years agowhoops stride already has +1 from SVSTATE class
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 14:46:46 +0000 (15:46 +0100)]
whoops stride already has +1 from SVSTATE class

2 years agoadd SVzd to REMAP (svshape) "stride"
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 14:40:16 +0000 (15:40 +0100)]
add SVzd to REMAP (svshape) "stride"
https://bugs.libre-soc.org/show_bug.cgi?id=930

2 years agoadd stride-multiplier for 2D DCT/FFT "in-place" offsets
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 14:36:29 +0000 (15:36 +0100)]
add stride-multiplier for 2D DCT/FFT "in-place" offsets
https://bugs.libre-soc.org/show_bug.cgi?id=930

2 years agoInitial SVP64 attempt to vpx_get4x4sse_cs_svp64_real()
Konstantinos Margaritis [Wed, 21 Sep 2022 14:28:49 +0000 (14:28 +0000)]
Initial SVP64 attempt to vpx_get4x4sse_cs_svp64_real()

2 years agouse mr instead of li/addi pair
Konstantinos Margaritis [Wed, 21 Sep 2022 14:28:14 +0000 (14:28 +0000)]
use mr instead of li/addi pair

2 years agofix comments
Konstantinos Margaritis [Wed, 21 Sep 2022 13:29:02 +0000 (13:29 +0000)]
fix comments

2 years agoadd vpx_get4x4sse_cs_svp64_real() and wrapper
Konstantinos Margaritis [Wed, 21 Sep 2022 13:07:03 +0000 (13:07 +0000)]
add vpx_get4x4sse_cs_svp64_real() and wrapper

2 years agoFirst form of fully working SVP64 version
Konstantinos Margaritis [Wed, 21 Sep 2022 13:06:13 +0000 (13:06 +0000)]
First form of fully working SVP64 version

2 years agoreduce number of iterations in test, as it takes too long
Konstantinos Margaritis [Wed, 21 Sep 2022 13:05:13 +0000 (13:05 +0000)]
reduce number of iterations in test, as it takes too long

2 years agonecessary changes for run_a_simulation to work with pypowersim_wrapper
Konstantinos Margaritis [Wed, 21 Sep 2022 08:50:13 +0000 (08:50 +0000)]
necessary changes for run_a_simulation to work with pypowersim_wrapper

2 years agoInitial attempt for SVP64 asm version of vpx_get_mb_ss_svp64_real()
Konstantinos Margaritis [Wed, 21 Sep 2022 08:49:11 +0000 (08:49 +0000)]
Initial attempt for SVP64 asm version of vpx_get_mb_ss_svp64_real()

2 years agoadd sv.madd* to sv_analysis
Luke Kenneth Casson Leighton [Wed, 21 Sep 2022 00:15:46 +0000 (01:15 +0100)]
add sv.madd* to sv_analysis

2 years agoadd sv.maddld test case
Jacob Lifshay [Wed, 21 Sep 2022 00:00:48 +0000 (17:00 -0700)]
add sv.maddld test case

2 years agominor codemorph, whitespace
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 23:46:18 +0000 (00:46 +0100)]
minor codemorph, whitespace

2 years agosv.bc reclassified as RM-2P-1S by eliminating SPRs.
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 20:27:33 +0000 (21:27 +0100)]
sv.bc reclassified as RM-2P-1S by eliminating SPRs.
strictly it should be RM-1P-1S but there is a bug. needs investigation.
sv_analysis temporarily classifies as twin predication for now

2 years agoPoC simplified and isolated unit test for libvpx (VP8 & VP9) that uses pypowersim_wrapper
Konstantinos Margaritis [Tue, 20 Sep 2022 20:16:25 +0000 (20:16 +0000)]
PoC simplified and isolated unit test for libvpx (VP8 & VP9) that uses pypowersim_wrapper

2 years agoInitial PoC for calling pypowersim from within C code
Konstantinos Margaritis [Tue, 20 Sep 2022 20:14:46 +0000 (20:14 +0000)]
Initial PoC for calling pypowersim from within C code

2 years agoremove messy string identification, use RM Mode from database
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 19:44:51 +0000 (20:44 +0100)]
remove messy string identification, use RM Mode from database
in sv/trans/svp64.py

2 years agoadd quick test and loooong test of pysvp64dis - branches split out
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 16:43:32 +0000 (17:43 +0100)]
add quick test and loooong test of pysvp64dis - branches split out

2 years agopysvp64asm: fix sz handling
Dmitry Selyutin [Tue, 20 Sep 2022 14:14:03 +0000 (17:14 +0300)]
pysvp64asm: fix sz handling

2 years agopower_insn: unify predicates
Dmitry Selyutin [Tue, 20 Sep 2022 13:39:56 +0000 (16:39 +0300)]
power_insn: unify predicates

2 years agotest_pysvp64dis: test vli specifier
Dmitry Selyutin [Tue, 20 Sep 2022 12:55:33 +0000 (15:55 +0300)]
test_pysvp64dis: test vli specifier

2 years agopysvp64asm: support vli specifier
Dmitry Selyutin [Tue, 20 Sep 2022 12:55:22 +0000 (15:55 +0300)]
pysvp64asm: support vli specifier

2 years agopower_insn: support vli specifier
Dmitry Selyutin [Tue, 20 Sep 2022 12:55:11 +0000 (15:55 +0300)]
power_insn: support vli specifier

2 years agopower_insn: simplify specifiers sorting
Dmitry Selyutin [Tue, 20 Sep 2022 11:36:18 +0000 (14:36 +0300)]
power_insn: simplify specifiers sorting

2 years agomissed one sorting order in test_pysvp64dis.py
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 11:13:43 +0000 (12:13 +0100)]
missed one sorting order in test_pysvp64dis.py

2 years agosort specifiers in pysvp64dis in lexicographical order
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 11:11:57 +0000 (12:11 +0100)]
sort specifiers in pysvp64dis in lexicographical order

2 years agoadd two extra tests, sv.bc/m=r3/sz
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 11:06:00 +0000 (12:06 +0100)]
add two extra tests, sv.bc/m=r3/sz

2 years agopower_insn: custom sz handling for branches
Dmitry Selyutin [Tue, 20 Sep 2022 10:23:44 +0000 (13:23 +0300)]
power_insn: custom sz handling for branches

2 years agopysvp64asm: update sz upon snz specifier
Dmitry Selyutin [Tue, 20 Sep 2022 10:23:15 +0000 (13:23 +0300)]
pysvp64asm: update sz upon snz specifier

2 years agoadd sv.bc/ctr/vsb unit test to test_pysvp64dis.py to show it is possible
Luke Kenneth Casson Leighton [Tue, 20 Sep 2022 09:56:56 +0000 (10:56 +0100)]
add sv.bc/ctr/vsb unit test to test_pysvp64dis.py to show it is possible

2 years agopower_insn: support vs/vsi/vsb/vsbi/ctr/cti specifiers
Dmitry Selyutin [Tue, 20 Sep 2022 00:45:48 +0000 (03:45 +0300)]
power_insn: support vs/vsi/vsb/vsbi/ctr/cti specifiers

2 years agopysvp64asm: support branch modes
Dmitry Selyutin [Mon, 19 Sep 2022 21:27:23 +0000 (00:27 +0300)]
pysvp64asm: support branch modes

2 years agopower_svp64_rm: sync it with tables
Dmitry Selyutin [Tue, 20 Sep 2022 00:32:37 +0000 (03:32 +0300)]
power_svp64_rm: sync it with tables

2 years agopower_insn: support common branch disassembly
Dmitry Selyutin [Mon, 19 Sep 2022 22:09:45 +0000 (01:09 +0300)]
power_insn: support common branch disassembly

2 years agopower_insn: simplify branch table
Dmitry Selyutin [Mon, 19 Sep 2022 21:47:09 +0000 (00:47 +0300)]
power_insn: simplify branch table

2 years agopower_insn: provide SVL/CTR branch fields
Dmitry Selyutin [Mon, 19 Sep 2022 21:24:37 +0000 (00:24 +0300)]
power_insn: provide SVL/CTR branch fields

2 years agoadd bc_ctr and bc_cti but not used yet
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 21:00:15 +0000 (22:00 +0100)]
add bc_ctr and bc_cti but not used yet

2 years agoprint out reg num in _check_regs, useful debug
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 20:56:44 +0000 (21:56 +0100)]
print out reg num in _check_regs, useful debug

2 years agotest_pysvp64dis: test els specifier
Dmitry Selyutin [Mon, 19 Sep 2022 20:29:31 +0000 (23:29 +0300)]
test_pysvp64dis: test els specifier

2 years agopower_insn: support els specifier
Dmitry Selyutin [Mon, 19 Sep 2022 20:27:45 +0000 (23:27 +0300)]
power_insn: support els specifier

2 years agocut cruft in caller.py
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 17:22:42 +0000 (18:22 +0100)]
cut cruft in caller.py

2 years agocodemorph on rc handling
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 16:04:05 +0000 (17:04 +0100)]
codemorph on rc handling

2 years agocodemorph
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 15:56:01 +0000 (16:56 +0100)]
codemorph

2 years agofirst interation (ha ha) src/dst iterators for ISACaller
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 15:44:54 +0000 (16:44 +0100)]
first interation (ha ha) src/dst iterators for ISACaller

2 years agocodemorph reduce indentation
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 14:30:26 +0000 (15:30 +0100)]
codemorph reduce indentation

2 years agocode cleanup on ISACaller write_output
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 14:21:31 +0000 (15:21 +0100)]
code cleanup on ISACaller write_output

2 years agorename to avoid conflict pred_dz from pred_dst_zero
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 12:31:23 +0000 (13:31 +0100)]
rename to avoid conflict pred_dz from pred_dst_zero

2 years agoanother code-morph splitting out the src/dst mask preparation
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 12:25:03 +0000 (13:25 +0100)]
another code-morph splitting out the src/dst mask preparation
from actual use of it to perform skipping (advancing src/dst step)

2 years agoadd function for calling a simulation
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 08:15:18 +0000 (09:15 +0100)]
add function for calling a simulation

2 years agoanother code-morph working towards getting the predicate-skipping
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 07:37:45 +0000 (08:37 +0100)]
another code-morph working towards getting the predicate-skipping
into the iterator-looping

2 years agowhitespace
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 07:22:26 +0000 (08:22 +0100)]
whitespace

2 years agocode-morph in StepLoop work towards splitting into iterators
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 07:21:54 +0000 (08:21 +0100)]
code-morph in StepLoop work towards splitting into iterators

2 years agoadd svstate param to constructor of StepLoop, ISACaller
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 07:12:41 +0000 (08:12 +0100)]
add svstate param to constructor of StepLoop, ISACaller

2 years agomove two big step/loop functions into separate class out of ISACaller
Luke Kenneth Casson Leighton [Mon, 19 Sep 2022 07:02:48 +0000 (08:02 +0100)]
move two big step/loop functions into separate class out of ISACaller

2 years agopower_insn: perform cleanup; turn comments into docstrings
Dmitry Selyutin [Sun, 18 Sep 2022 21:57:09 +0000 (00:57 +0300)]
power_insn: perform cleanup; turn comments into docstrings

2 years agocode-comments identifying tables
Luke Kenneth Casson Leighton [Sun, 18 Sep 2022 21:19:43 +0000 (22:19 +0100)]
code-comments identifying tables

2 years agosimplify predicate mask reporting. assign dw=sw=mask then test 2P
Luke Kenneth Casson Leighton [Sun, 18 Sep 2022 21:17:22 +0000 (22:17 +0100)]
simplify predicate mask reporting. assign dw=sw=mask then test 2P
and assign sw new value

2 years agouse widths.get(dw/sw) and test empty/non-empty after.
Luke Kenneth Casson Leighton [Sun, 18 Sep 2022 21:08:04 +0000 (22:08 +0100)]
use widths.get(dw/sw) and test empty/non-empty after.

2 years agofix predicate mask case when smask was zero but mmode was not
Luke Kenneth Casson Leighton [Sun, 18 Sep 2022 20:59:57 +0000 (21:59 +0100)]
fix predicate mask case when smask was zero but mmode was not
quick/easy way: use predicates.get((mmode,smask)) and if empty skip
added stack of tests, 1P and 2P, to test_pysvp64dis.py

2 years agono, better than hack-job, stop CROpSimpleRM deriving from MRBaseRM
Luke Kenneth Casson Leighton [Sun, 18 Sep 2022 20:34:39 +0000 (21:34 +0100)]
no, better than hack-job, stop CROpSimpleRM deriving from MRBaseRM
that way it can handle "/rg" on its own