3 This page covers and coordinates implementing SV. The basic concept is
4 to go step-by-step through the [[sv/overview]] adding each feature,
5 one at a time. Caveats and notes are included so that other implementors may avoid some common pitfalls.
9 * <http://lists.libre-soc.org/pipermail/libre-soc-dev/2021-January/001865.html>
10 * <https://bugs.libre-soc.org/show_bug.cgi?id=578> python-based svp64
12 * <https://bugs.libre-soc.org/show_bug.cgi?id=579> c/c++ macro svp64
14 * <https://bugs.libre-soc.org/show_bug.cgi?id=586> microwatt svp64-decode1.vhdl autogenerator
15 * <https://bugs.libre-soc.org/show_bug.cgi?id=577> gcc/binutils/svp64
16 * <https://bugs.libre-soc.org/show_bug.cgi?id=241> gem5 / ISACaller simulator
17 - <https://bugs.libre-soc.org/show_bug.cgi?id=581> gem5 upstreaming
18 * <https://bugs.libre-soc.org/show_bug.cgi?id=583> TestIssuer
19 * <https://bugs.libre-soc.org/show_bug.cgi?id=588> PowerDecoder2
20 * <https://bugs.libre-soc.org/show_bug.cgi?id=587> setvl ancillary tasks
21 (instruction form SVL-Form, field designations, pseudocode, SPR allocation)
22 * <https://bugs.libre-soc.org/show_bug.cgi?id=615> agree sv assembly syntax
23 * <https://bugs.libre-soc.org/show_bug.cgi?id=617> TestIssuer add single/twin Predication
27 There are five projects:
29 * TestIssuer (the HDL)
30 * ISACaller (the python-based simulator)
31 * power-gem5 (a cycle accurate simulator)
35 Each of these needs to have SV augmentation, and the best way to
36 do it is if they are all done at the same time, implementing the same
41 These are prerequisite tasks:
43 * power-gem5 automanagement, similar to pygdbmi for starting qemu
44 - found this <https://www.gem5.org/documentation/general_docs/debugging_and_testing/debugging/debugging_simulated_code>
46 - remote gdb should work <https://github.com/power-gem5/gem5/blob/gem5-experimental/src/arch/power/remote_gdb.cc>
47 * c++, c and python macros for generating [[sv/svp64]] assembler
49 - python svp64 underway, minimalist sufficient for FU unit tests
50 <https://git.libre-soc.org/?p=soc.git;a=blob;f=src/soc/sv/trans/svp64.py;hb=HEAD>
51 * PowerDecoder2 - both TestIssuer and ISACaller are dependent on this
52 - <https://bugs.libre-soc.org/show_bug.cgi?id=588> underway
53 - INT and CR EXTRA svp64 fields completed.
54 * SVP64PowerDecoder2, used to identify SVP64 Prefixes. DONE.
56 People coordinating different tasks. This doesn't mean exclusive work on these areas it just means they are the "coordinator" and lead:
59 * Jacob: C/C++ header for using SV through inline assembly
60 * Cesar: TestIssuer FSM
63 * Luke: ISACaller, python-assembler-generator-class
65 * Alexandre: binutils-svp64-assembler and gcc
70 order: listed in [[sv/overview]]
74 An autogenerator containing CSV files is available so that the task of creating decoders is not burdensome. sv_analyse.py creates the CSV files, SVP64RM class picks them up.
76 * ISACaller: part done. svp64 detected, PowerDecoder2 in use
78 * TestIssuer: part done. svp64 detected, PowerDecoder2 in use.
79 * Microwatt: TODO, started auto-generated sv_decode.vhdl
80 * python-based assembler-translator: 40% done (lkcl)
81 * c++ macros: underway (jacob)
83 Note when decoding the RM into bits different modes that LDST interprets the 5 mode bits differently not just on whether it is LD/ST bit also what *type* of LD/ST. Immediate LD/ST is further qualified to indicate if it operates in element-strided or unit-strided mode. However Indexed LD/ST is not.
85 **IMPORTANT**! when spotting RA=0 in some instructions it is critical to note that the *full **seven** bits* are used (those from EXTRA2/3 included) because RA is no longer only five bits.
89 * <https://git.libre-soc.org/?p=libreriscv.git;a=blob;f=openpower/sv_analysis.py;hb=HEAD>
90 * <https://git.libre-soc.org/?p=soc.git;a=blob;f=src/soc/decoder/power_svp64.py;hb=HEAD>
91 * <https://git.libre-soc.org/?p=soc.git;a=blob;f=src/soc/decoder/power_svp64_rm.py;hb=HEAD>
95 This is a peer of MSR but is stored in an SPR. It should be considered part of the state of PC+MSR because SVSTATE is effectively a Sub-PC.
97 Chosen values, fitting with v3.1B p12 "Sandbox" guidelines:
101 720,SVSRR0,yes,yes,32
110 * <https://git.libre-soc.org/?p=soc.git;a=blob;f=src/soc/sv/svstate.py;hb=HEAD>
112 ## Adding SVSTATE "set/get" support for hw/sw debugging
114 This includes adding DMI get/set support in hardware as well as gdb (remote) support.
116 * LibreSOC DMI/JTAG: TODO
117 * Microwatt DMI: TODO
118 * power-gem5 remote gdb: TODO
119 * TestIssuer: DONE (read-only at least) <https://git.libre-soc.org/?p=soc.git;a=commitdiff;h=4d5482810c980ff927ccec62968a40a490ea86eb>
123 * <https://bugs.libre-soc.org/show_bug.cgi?id=609>
127 a [[sv/setvl]] instruction is needed, which also implements [[sv/sprs]] i.e. primarily the `SVSTATE` SPR. the dual-access SPRs for VL and MVL which mirror into the SVSTATE.VL and SVSTATE.MVL fields are not immediately essential to implement.
129 * LibreSOC OpenPOWER wiki fields/forms: DONE. pseudocode: TODO
137 ## SVSRR0 for exceptions
139 SV's SVSTATE context is effectively a Sub-PC. On exceptions the PC is saved into SRR0: it should come as no surprise that SVSTATE must be treated exactly the same. SVSRR0 therefore is added to the list to be saved/restored in **exactly** the same way and time as SRR0 and SRR1. This is fundamental and absolutely critical to view SVSTATE as a full peer of PC (CIA, NIA).
146 ## Illegal instruction exceptions
148 Anything not listed as SVP64 extended must raise an illegal exception if prefixed. setvl, branch, mtmsr, mfmsr at the minimum.
157 main SV for-loop, as a FSM, updating `SVSTATE.srcstep`, using it as the index in the for-loop from 0 to VL-1. Register numbers are incremented by one if marked as vector.
159 *This loop goes in between decode and issue phases*. It is as if there were multiple sequential instructions in the instruction stream *and the loop must be treated as such*. Specifically: all register read and write hazards **MUST** be respected; the Program Order must be respected even though and especially because this is Sub-PC execution.
161 This **includes** any exceptions, hence why SVSTATE exists and why SVSRR0 must be used to store SVSTATE alongside when SRR0 and SRR1 store PC and MSR.
163 Due to the need for exceptions to occur in the middle, the loop should *not* be implemented as an actual for-loop, whilst recognising that optimised implementations may do multi-issue element execution as long as Program Order is preserved, just as it would be for the PC.
165 * ISACaller: DONE, first revision <https://git.libre-soc.org/?p=soc.git;a=commitdiff;h=9078b2935beb4ba89dcd2af91bb5e3a0bcffbe71>
168 - part done <https://git.libre-soc.org/?p=soc.git;a=commitdiff;h=92ba64ea13794dea71816be746a056d52e245651>
169 - done <https://git.libre-soc.org/?p=soc.git;a=commitdiff;h=97136d71397f420479d601dcb80f0df4abf73d22>
172 Remember the following register files need to have for-loops, plus
176 * SPRs (yes, really: mtspr and mfspr are SV Context-extensible)
177 * Condition Registers. see note below
180 When Rc=1 is encountered in an SVP64 Context the destination is different (TODO) i.e. not CR0 or CR1. Implicit Rc=1 Condition Registers are still Vectorised but do **not** have EXTRA2/3 spec adjustments. The only part if the EXTRA2/3 spec that is observed and respected is whether the CR is Vectorised (isvec).
182 ## Increasing register file sizes
184 TODO. INTs, FPs, CRs, these all increase to 128. Welcome To Vector ISAs.
186 At the same time the `Rc=1` CR offsets normslly CR0 and CR1 for fixed and FP scalar may also be adjusted.
188 ## Single and Twin Predication
190 * <https://bugs.libre-soc.org/show_bug.cgi?id=617> TestIssuer
192 ## Element width overrides