Provided by: llvm-12_12.0.1-19ubuntu3_amd64 bug

NAME

       llvm-rtdyld - manual page for llvm-rtdyld 12

DESCRIPTION

       OVERVIEW: llvm MC-JIT tool

       USAGE: llvm-rtdyld [options] <input files> --args <program arguments>...

       OPTIONS:

       Color Options:

       --color                                                -     Use    colors    in    output
              (default=autodetect)

       General options:

       --aarch64-neon-syntax=<value>                      - Choose style of  NEON  code  to  emit
              from AArch64 backend:

       =generic
              -   Emit generic NEON assembly

       =apple -   Emit Apple-style NEON assembly

       --abort-on-max-devirt-iterations-reached            -  Abort  when  the max iterations for
              devirtualization CGSCC repeat pass is reached

       --amdgpu-bypass-slow-div                           - Skip 64-bit divide for dynamic 32-bit
              values

       --amdgpu-disable-loop-alignment                    - Do not align and prefetch loops

       --amdgpu-disable-power-sched                        -  Disable  scheduling to minimize mAI
              power bursts

       --amdgpu-dpp-combine                               - Enable DPP combiner

       --amdgpu-dump-hsa-metadata                         - Dump AMDGPU HSA Metadata

       --amdgpu-enable-flat-scratch                       - Use flat scratch instructions

       --amdgpu-enable-merge-m0                           - Merge and hoist M0 initializations

       --amdgpu-promote-alloca-to-vector-limit=<uint>     - Maximum byte size to consider promote
              alloca to vector

       --amdgpu-reserve-vgpr-for-sgpr-spill                -  Allocates  one VGPR for future SGPR
              Spill

       --amdgpu-sdwa-peephole                             - Enable SDWA peepholer

       --amdgpu-use-aa-in-codegen                         - Enable the use of AA during codegen.

       --amdgpu-verify-hsa-metadata                       - Verify AMDGPU HSA Metadata

       --amdgpu-vgpr-index-mode                           - Use  GPR  indexing  mode  instead  of
              movrel for vector indexing

       --args <string>...                                 - <program arguments>...

       --arm-add-build-attributes                         -

       --arm-implicit-it=<value>                            -   Allow   conditional  instructions
              outdside of an IT block

       =always
              -   Accept in both ISAs, emit implicit ITs in Thumb

       =never -   Warn in ARM, reject in Thumb

       =arm   -   Accept in ARM, reject in Thumb

       =thumb -   Warn in ARM, emit implicit ITs in Thumb

       --atomic-counter-update-promoted                   - Do counter update using atomic  fetch
       add
              for promoted counters only

       --atomic-first-counter                              -  Use  atomic  fetch  add  for  first
              counter in a function (usually the entry counter)

       --bounds-checking-single-trap                      - Use one trap block per function

       --cfg-hide-deoptimize-paths                        -

       --cfg-hide-unreachable-paths                       -

       --check=<string>                                   - File containing RuntimeDyld  verifier
              checks.

       --cost-kind=<value>                                - Target cost kind

       =throughput
              -   Reciprocal throughput

       =latency
              -   Instruction latency

       =code-size
              -   Code size

       =size-latency
              -   Code size and latency

       --cvp-dont-add-nowrap-flags                        -

       --debugify-level=<value>                           - Kind of debug info to add

       =locations
              -   Locations only

       =location+variables
              -   Locations and Variables

       --debugify-quiet                                   - Suppress verbose debugify output

       --disable-promote-alloca-to-lds                    - Disable promote alloca to LDS

       --disable-promote-alloca-to-vector                 - Disable promote alloca to vector

       --do-counter-promotion                             - Do counter register promotion

       --dot-cfg-mssa=<file name for generated dot file>  - file name for generated dot file

       --dylib=<string>                                   - Add library.

       --emscripten-cxx-exceptions-allowed=<string>        -  The list of function names in which
              Emscripten-style    exception    handling    is     enabled     (see     emscripten
              EMSCRIPTEN_CATCHING_ALLOWED options)

       --enable-cse-in-irtranslator                       - Should enable CSE in irtranslator

       --enable-cse-in-legalizer                          - Should enable CSE in Legalizer

       --enable-emscripten-cxx-exceptions                    -    WebAssembly    Emscripten-style
              exception handling

       --enable-emscripten-sjlj                              -    WebAssembly    Emscripten-style
              setjmp/longjmp handling

       --enable-gvn-hoist                                 - Enable the GVN hoisting pass (default
              = off)

       --enable-gvn-memdep                                -

       --enable-gvn-sink                                  - Enable the GVN sinking pass  (default
              = off)

       --enable-load-in-loop-pre                          -

       --enable-load-pre                                  -

       --enable-loop-simplifycfg-term-folding             -

       --enable-name-compression                             -    Enable   name/filename   string
              compression

       --enable-split-backedge-in-load-pre                -

       --entry=<string>                                   - Function to call as entry point.

       --gpsize=<uint>                                    - Global Pointer Addressing Size.
              The default size is 8.

       --hash-based-counter-split                         - Rename counter variable of  a  comdat
              function based on cfg hash

       --hot-cold-split                                   - Enable hot-cold splitting pass

       --import-all-index                                  -  Import  all  external  functions in
              index.

       --instcombine-code-sinking                         - Enable code sinking

       --instcombine-guard-widening-window=<uint>         - How wide  an  instruction  window  to
              bypass looking for another guard

       --instcombine-max-iterations=<uint>                  -   Limit   the   maximum  number  of
              instruction combining iterations

       --instcombine-max-num-phis=<uint>                  - Maximum  number  phis  to  handle  in
              intptr/ptrint folding

       --instcombine-maxarray-size=<uint>                  -  Maximum  array size considered when
              doing a combine

       --instcombine-negator-enabled                      - Should we attempt to sink negations?

       --instcombine-negator-max-depth=<uint>             - What is the maximal lookup depth when
              trying to check for viability of negation sinking.

       --instcombine-unsafe-select-transform              - Enable poison-unsafe select to and/or
              transform

       --instrprof-atomic-counter-update-all              -  Make  all  profile  counter  updates
              atomic (for testing only)

       --internalize-public-api-file=<filename>            -  A  file  containing  list of symbol
              names to preserve

       --internalize-public-api-list=<list>               - A list of symbol names to preserve

       --iterative-counter-promotion                      - Allow counter  promotion  across  the
              whole loop nest.

       --lto-embed-bitcode=<value>                         -  Embed  LLVM bitcode in object files
              produced by LTO

       =none  -   Do not embed

       =optimized
              -   Embed after all optimization passes

       =post-merge-pre-opt
              -   Embed post merge, but before optimizations

       --lto-pass-remarks-filter=<regex>                  - Only record optimization remarks from
              passes whose names match the given regular expression

       --lto-pass-remarks-format=<format>                  -  The  format  used  for  serializing
              remarks (default: YAML)

       --lto-pass-remarks-output=<filename>               - Output filename for pass remarks

       --matrix-default-layout=<value>                    - Sets the default matrix layout

       =column-major
              -   Use column-major layout

       =row-major
              -   Use row-major layout

       --max-counter-promotions=<int>                      -  Max  number  of   allowed   counter
              promotions

       --max-counter-promotions-per-loop=<uint>            -  Max  number  counter promotions per
              loop to avoid increasing register pressure too much

       --mcpu=<cpu-name>                                   -   Target   a   specific   cpu   type
              (-mcpu=help for details)

       --merror-missing-parenthesis                        - Error for missing parenthesis around
              predicate registers

       --merror-noncontigious-register                    - Error for register names that  aren't
              contigious

       --mhvx                                             - Enable Hexagon Vector eXtensions

       --mhvx=<value>                                     - Enable Hexagon Vector eXtensions

       =v60   -   Build for HVX v60

       =v62   -   Build for HVX v62

       =v65   -   Build for HVX v65

       =v66   -   Build for HVX v66

       =v67   -   Build for HVX v67

       --mips-compact-branches=<value>                    - MIPS Specific: Compact branch policy.

       =never
              -   Do not use compact branches if possible.

       =optimal
              -   Use compact branches where appropriate (default).

       =always
              -   Always use compact branches if possible.

       --mips16-constant-islands                          - Enable mips16 constant islands.

       --mips16-hard-float                                - Enable mips16 hard float.

       --mir-strip-debugify-only                           -  Should  mir-strip-debug  only strip
              debug info from debugified modules by default

       --mno-compound                                      -   Disable   looking   for   compound
              instructions for Hexagon

       --mno-fixup                                           -   Disable   fixing   up   resolved
              relocations for Hexagon

       --mno-ldc1-sdc1                                    - Expand  double  precision  loads  and
              stores to their single precision counterparts

       --mno-pairing                                         -   Disable   looking   for   duplex
              instructions for Hexagon

       --mwarn-missing-parenthesis                        - Warn for missing  parenthesis  around
              predicate registers

       --mwarn-noncontigious-register                      -  Warn  for register names that arent
              contigious

       --mwarn-sign-mismatch                              - Warn for  mismatching  a  signed  and
              unsigned value

       --no-discriminators                                 -  Disable generation of discriminator
              information.

       --nvptx-sched4reg                                  - NVPTX Specific: schedule for register
              pressue

       --poison-checking-function-local                    -  Check  that  returns are non-poison
              (for testing)

       --preallocate=<ulong>                              - Allocate memory upfront  rather  than
              on-demand

       --r600-ir-structurize                              - Use StructurizeCFG IR pass

       --rdf-dump                                         -

       --rdf-limit=<uint>                                 -

       --runtime-counter-relocation                         -   Enable   relocating  counters  at
              runtime.

       --safepoint-ir-verifier-print-only                 -

       --sample-profile-check-record-coverage=<N>         - Emit a warning if  less  than  N%  of
              records in the input profile are matched to the IR.

       --sample-profile-check-sample-coverage=<N>          -  Emit  a  warning if less than N% of
              samples in the input profile are matched to the IR.

       --sample-profile-max-propagate-iterations=<uint>   - Maximum number of  iterations  to  go
              through when propagating sample block/edge weights through the CFG.

       --show-times                                       - Show times for llvm-rtdyld phases

       --skip-ret-exit-block                               -  Suppress  counter promotion if exit
              blocks contain ret.

       --speculative-counter-promotion-max-exiting=<uint> - The max number of exiting blocks of a
       loop to allow
              speculative counter promotion

       --speculative-counter-promotion-to-loop             -  When  the  option  is false, if the
       target block is in a loop, the promotion will be disallowed unless the promoted counter
              update can be further/iteratively promoted into an acyclic  region.

       --summary-file=<string>                            - The summary file to use for  function
              importing.

       --tail-predication=<value>                         - MVE tail-predication pass options

       =disabled
              -   Don't tail-predicate loops

       =enabled-no-reductions
              -   Enable tail-predication, but not for reduction loops

       =enabled
              -   Enable tail-predication, including reduction loops

       =force-enabled-no-reductions
              -    Enable  tail-predication,  but  not  for reduction loops, and force this which
              might be unsafe

       =force-enabled
              -   Enable tail-predication, including reduction loops, and force this which  might
              be unsafe

       --thinlto-assume-merged                              -   Assume   the  input  has  already
              undergone ThinLTO  function  importing  and  the  other  pre-optimization  pipeline
              changes.

       --threads=<int>                                    -

       --triple=<string>                                  - Target triple for disassembler

              Action to perform:

       --execute                                         - Load, link, and execute the inputs.

       --printline                                       - Load, link, and print line information
              for each function.

       --printdebugline                                  - Load, link, and print line information
              for each function using the debug object

       --printobjline                                     - Like -printlineinfo but does not load
              the object first

       --verify                                          - Load, link and  verify  the  resulting
              memory image.

       --verify-region-info                               - Verify region info (time consuming)

       --vp-counters-per-site=<number>                      -   The  average  number  of  profile
              counters allocated per value profiling site.

       --vp-static-alloc                                  -  Do  static  counter  allocation  for
              value profiler

       --x86-align-branch=<string>                         -  Specify  types of branches to align
       (plus separated list of types):
              jcc      indicates conditional jumps fused    indicates fused conditional jumps jmp
              indicates  direct  unconditional jumps call     indicates direct and indirect calls
              ret      indicates rets indirect indicates indirect unconditional jumps

       --x86-align-branch-boundary=<uint>                 -  Control  how  the  assembler  should
              align branches with NOP. If the boundary's size is not 0, it should be a power of 2
              and no less than 32. Branches will be aligned  to  prevent  from  being  across  or
              against  the  boundary  of  specified  size.  The  default  value  0 does not align
              branches.

       --x86-branches-within-32B-boundaries                -  Align  selected   instructions   to
       mitigate negative performance impact of Intel's micro code update for errata skx102.
              May  break  assumptions  about labels corresponding to particular instructions, and
              should be used with caution.

       --x86-pad-max-prefix-size=<uint>                   - Maximum number of prefixes to use for
              padding

       Generic Options:

       --help                                                -    Display    available    options
              (--help-hidden for more)

       --help-list                                        - Display  list  of  available  options
              (--help-list-hidden for more)

       --version                                          - Display the version of this program

       Polly Options: Configure the polly loop optimizer

       --polly                                             -  Enable the polly optimizer (only at
              -O3)

       --polly-2nd-level-tiling                           - Enable  a  2nd  level  loop  of  loop
              tiling

       --polly-ast-print-accesses                         - Print memory access functions

       --polly-context=<isl parameter set>                - Provide additional constraints on the
              context parameters

       --polly-dce-precise-steps=<int>                    - The number of precise  steps  between
              two  approximating iterations. (A value of -1 schedules another approximation stage
              before the actual dead code elimination.

       --polly-delicm-max-ops=<int>                       - Maximum number of isl  operations  to
              invest for lifetime analysis; 0=no limit

       --polly-detect-full-functions                      - Allow the detection of full functions

       --polly-dump-after                                    -    Dump    module    after   Polly
              transformations into a file suffixed with "-after"

       --polly-dump-after-file=<string>                     -    Dump    module    after    Polly
              transformations to the given file

       --polly-dump-before                                   -    Dump    module   before   Polly
              transformations into a file suffixed with "-before"

       --polly-dump-before-file=<string>                    -   Dump    module    before    Polly
              transformations to the given file

       --polly-enable-simplify                            - Simplify SCoP after optimizations

       --polly-ignore-func=<string>                        - Ignore functions that match a regex.
              Multiple regexes can be comma separated. Scop detection will ignore  all  functions
              that match ANY of the regexes provided.

       --polly-isl-arg=<argument>                         - Option passed to ISL

       --polly-on-isl-error-abort                         - Abort if an isl error is encountered

       --polly-only-func=<string>                          -  Only  run on functions that match a
              regex. Multiple regexes can be comma separated. Scop  detection  will  run  on  all
              functions that match ANY of the regexes provided.

       --polly-only-region=<identifier>                    -  Only  run  on  certain regions (The
              provided identifier must appear in the name of the region's entry block

       --polly-only-scop-detection                        - Only run scop detection, but no other
              optimizations

       --polly-optimized-scops                             -  Polly - Dump polyhedral description
              of Scops optimized with the isl scheduling optimizer and the set of post-scheduling
              transformations is applied on the schedule tree

       --polly-parallel                                    -  Generate  thread parallel code (isl
              codegen only)

       --polly-parallel-force                             - Force generation of  thread  parallel
              code ignoring any cost model

       --polly-pattern-matching-based-opts                  -   Perform  optimizations  based  on
              pattern matching

       --polly-process-unprofitable                       - Process scops that  are  unlikely  to
              benefit from Polly optimizations.

       --polly-register-tiling                            - Enable register tiling

       --polly-report                                       -   Print   information   about   the
              activities of Polly

       --polly-show                                       - Highlight the code regions that  will
              be optimized in a (CFG BBs and LLVM-IR instructions)

       --polly-show-only                                   - Highlight the code regions that will
              be optimized in a (CFG only BBs)

       --polly-stmt-granularity=<value>                   - Algorithm to use for splitting  basic
              blocks into multiple statements

       =bb    -   One statement per basic block

       =scalar-indep
              -   Scalar independence heuristic

       =store -   Store-level granularity

       --polly-target=<value>                             - The hardware to target

       =cpu   -   generate CPU code

       --polly-tiling                                     - Enable loop tiling

       --polly-vectorizer=<value>                         - Select the vectorization strategy

       =none  -   No Vectorization

       =polly -   Polly internal vectorizer

       =stripmine
              -   Strip-mine outer loops for the loop-vectorizer to trigger