Page MenuHomePhabricator

rochauha (Ronak Chauhan)
User

Projects

User does not belong to any projects.

User Details

User Since
May 23 2020, 10:36 AM (17 w, 14 h)

Recent Activity

Wed, Sep 9

rochauha added a reverting change for rG487a80531006: [AMDGPU] Support disassembly for AMDGPU kernel descriptors: rGf078577f31cc: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors".
Wed, Sep 9, 5:34 AM
rochauha committed rGf078577f31cc: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors" (authored by rochauha).
Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors"
Wed, Sep 9, 5:34 AM
rochauha added a reverting change for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors: rGf078577f31cc: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors".
Wed, Sep 9, 5:34 AM · Restricted Project

Tue, Sep 8

rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

3 of the test cases - kd-sgpr.s, kd-vgpr.s, kd-zeroed-gfx10.s fail with the PowerPC buildbot (http://lab.llvm.org:8011/builders/clang-ppc64be-linux/builds/53608). From what I understand, these tests should only run if AMDGPU target is built. The lit.local.cfg file specifies that.

Tue, Sep 8, 11:22 AM · Restricted Project
rochauha committed rG487a80531006: [AMDGPU] Support disassembly for AMDGPU kernel descriptors (authored by rochauha).
[AMDGPU] Support disassembly for AMDGPU kernel descriptors
Tue, Sep 8, 8:58 AM
rochauha closed D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Tue, Sep 8, 8:57 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Changes based on comments by @jhenderson.

Tue, Sep 8, 2:55 AM · Restricted Project

Mon, Sep 7

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Mon, Sep 7, 4:48 AM · Restricted Project
rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Mon, Sep 7, 4:41 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Changes based on comments by @jhenderson

  • Used llvm::cantFail(C.takeError()) to handle error.
  • Removed blank lines at the end of test files.
  • Streamlined beginning of comments.
  • Used split-file tool to separate SGPR and VGPR test cases.
Mon, Sep 7, 4:39 AM · Restricted Project

Aug 19 2020

rochauha added a reverting change for rGcacfb02d28a3: [AMDGPU] Support disassembly for AMDGPU kernel descriptors: rGfdf71d486c0f: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors".
Aug 19 2020, 12:44 AM
rochauha committed rGfdf71d486c0f: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors" (authored by rochauha).
Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors"
Aug 19 2020, 12:43 AM
rochauha added a reverting change for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors: rGfdf71d486c0f: Revert "[AMDGPU] Support disassembly for AMDGPU kernel descriptors".
Aug 19 2020, 12:43 AM · Restricted Project

Aug 18 2020

rochauha committed rGcacfb02d28a3: [AMDGPU] Support disassembly for AMDGPU kernel descriptors (authored by rochauha).
[AMDGPU] Support disassembly for AMDGPU kernel descriptors
Aug 18 2020, 8:19 PM
rochauha closed D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Aug 18 2020, 8:19 PM · Restricted Project
rochauha committed rG7b777ee73077: [ELF] Hide target specific methods as private (authored by rochauha).
[ELF] Hide target specific methods as private
Aug 18 2020, 5:57 AM
rochauha closed D86136: [ELF] Hide target specific methods as private.
Aug 18 2020, 5:57 AM · Restricted Project
rochauha requested review of D86136: [ELF] Hide target specific methods as private.
Aug 18 2020, 5:46 AM · Restricted Project
rochauha added a comment to D84519: [llvm-objdump][AMDGPU] Detect CPU string.

I have manually aligned the comment to the case statement before landing the patch. I think some investigation for clang-format may be necessary.

Aug 18 2020, 5:16 AM · Restricted Project
rochauha committed rGe760e85680d6: [llvm-objdump][AMDGPU] Detect CPU string (authored by rochauha).
[llvm-objdump][AMDGPU] Detect CPU string
Aug 18 2020, 5:14 AM
rochauha closed D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 18 2020, 5:14 AM · Restricted Project

Aug 17 2020

rochauha updated the summary of D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Aug 17 2020, 10:50 PM · Restricted Project
rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Can I consider this patch to be at NFC stage?

Aug 17 2020, 10:43 PM · Restricted Project
rochauha added a comment to D84519: [llvm-objdump][AMDGPU] Detect CPU string.

LGTM, and can you please open a follow-up review once this is committed to hide all of the Object::get<Target><Stuff> methods?

Aug 17 2020, 10:41 PM · Restricted Project
rochauha added inline comments to D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 17 2020, 10:40 PM · Restricted Project

Aug 15 2020

rochauha updated the diff for D84519: [llvm-objdump][AMDGPU] Detect CPU string.
  • Removed comment and braces.
Aug 15 2020, 10:03 PM · Restricted Project

Aug 14 2020

rochauha updated the diff for D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 14 2020, 11:45 PM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Updated tests and added a failure test.
  • Checking error when cursor holds Error::success() while handling failure cases.
  • Removed Size from subroutines' signatures as we aren't tracking the size.
Aug 14 2020, 11:04 PM · Restricted Project

Aug 8 2020

rochauha abandoned D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.

Based on comments and discussion, the difference for GFX9 is being handled using allocation granule sizes and no change is required.

Aug 8 2020, 1:00 AM · Restricted Project
rochauha added inline comments to D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 8 2020, 12:56 AM · Restricted Project
rochauha updated the summary of D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 8 2020, 12:53 AM · Restricted Project
rochauha updated the summary of D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 8 2020, 12:53 AM · Restricted Project
rochauha updated the diff for D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 8 2020, 12:51 AM · Restricted Project
rochauha added inline comments to D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Aug 8 2020, 12:50 AM · Restricted Project

Aug 6 2020

rochauha updated the diff for D84519: [llvm-objdump][AMDGPU] Detect CPU string.
  • Pulled CPU string detection logic into ELFObjectFileBase.
  • Added details in commit message.
Aug 6 2020, 11:29 PM · Restricted Project
rochauha added a comment to D84519: [llvm-objdump][AMDGPU] Detect CPU string.

To me, it doesn't look like this is 'real' target-specific work. For example the target triple is detected within llvm-objdump itself using the getTarget() function. I'd like to understand - what is different in case CPU string detection that it needs to reside somewhere else?

Aug 6 2020, 1:01 AM · Restricted Project

Aug 5 2020

rochauha retitled D84519: [llvm-objdump][AMDGPU] Detect CPU string from [llvm-objdump][AMDGPU] Detect subtarget to [llvm-objdump][AMDGPU] Detect CPU string.
Aug 5 2020, 2:23 AM · Restricted Project
rochauha added a comment to D84519: [llvm-objdump][AMDGPU] Detect CPU string.

I am a bit worrisome that this patch is adding more target specific stuff to llvm-objdump.

Agreed, I have looked at making the majority of llvm-objdump (and essentially everything under tools/) into a library at one point, but the biggest initial hurdle is the CommandLine parsing library. I think ideally all of the target-relevant parts would be in target-overridden implementations in some library, all of the llvm-objdump behavior parts (like the core symbol-to-symbol loop) would be in an llvm-objdump library which depends on the libraries with target-specific behaviors, and the tools/ directory would contain ~10 line main functions.

Can we step back and think whether precise CPU selection is really necessary? For example, PowerPC has the needs for different ISA levels but it simply uses -mcpu=future.

I am a bit lost on what you mean; is there a significant cost to providing precise CPU selection? It doesn't make sense to require the user to e.g. run the dumper to inspect the binary in order to come up with the command-line to run the dumper in order to inspect the binary.

If different AMDGPU CPUs are incompatible, should such detection be moved to somewhere in lib/Target/AMDGPU/?

Yes, I think it should be done in a generic way. All other targets which don't need/want it just getting the default (existing) behavior.

Aug 5 2020, 1:53 AM · Restricted Project

Jul 28 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 28 2020, 3:59 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Got rid of raw number and added an enum for offsets.
  • Added new tests.
  • Updated the nop-data.ll test so that it passes with this patch.
Jul 28 2020, 3:58 AM · Restricted Project

Jul 25 2020

rochauha added inline comments to D84519: [llvm-objdump][AMDGPU] Detect CPU string.
Jul 25 2020, 4:18 AM · Restricted Project
rochauha updated the diff for D84519: [llvm-objdump][AMDGPU] Detect CPU string.

Some changes based on review by @scott.linder.

Jul 25 2020, 4:18 AM · Restricted Project
rochauha added a comment to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.

I discussed with Tony today, and I was thinking about this the wrong way.

SPI does not require the granule count to be even, it just rounds up the granule count before actually performing the allocation. This means, from the compiler's perspective, when it is calculating things like the AMDGPU::IsaInfo::getMaxNumSGPRs it must consider the "allocation" granule size (IsaInfo::getSGPRAllocGranule). Conversely, from the assembler/diassembler perspective, it must consider the "encoding" granule size (IsaInfo::getSGPREncodingGranule). It is perfectly OK to have a GFX9 code object with a granulated SGPR count of 1, and we should allow emitting that in the assembler so that the disassembler can accurately reproduce those code objects.

I don't think there is any fix needed here, we already separate these two concepts and correctly apply them elsewhere. I think I just led you astray in the disassembly patch; you should only be using the encoding granule size, and shouldn't need any special handling for e.g. GFX9 to handle the fact that the allocation and encoding granule sizes are not equal.

Jul 25 2020, 3:13 AM · Restricted Project

Jul 24 2020

Herald added a project to D84519: [llvm-objdump][AMDGPU] Detect CPU string: Restricted Project.
Jul 24 2020, 5:06 AM · Restricted Project

Jul 23 2020

rochauha added inline comments to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.
Jul 23 2020, 1:55 AM · Restricted Project
rochauha updated the diff for D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.

Added missing std::max.

Jul 23 2020, 1:54 AM · Restricted Project

Jul 22 2020

rochauha added inline comments to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.
Jul 22 2020, 11:59 AM · Restricted Project
rochauha updated the diff for D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.

Updated patch based on comments.
Updated old tests.
Added new test.

Jul 22 2020, 11:57 AM · Restricted Project
rochauha updated the summary of D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.
Jul 22 2020, 11:45 AM · Restricted Project

Jul 21 2020

rochauha added a comment to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.

Needs test

Jul 21 2020, 8:40 AM · Restricted Project
rochauha added inline comments to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9.
Jul 21 2020, 8:29 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Switched to disassembling as numerical value rather than .amdgcn.next_free_sgpr.

Jul 21 2020, 5:15 AM · Restricted Project

Jul 20 2020

Herald added a project to D84194: [AMDGPU] Correct the number of SGPR blocks used for GFX9: Restricted Project.
Jul 20 2020, 9:16 PM · Restricted Project

Jul 15 2020

rochauha added a comment to D83801: [MC] Pass the section to onSymbolStart() for more context.

Can you demonstrate how you are going to use the new interface?

The note section in AMDGPU ELF objects contains metadata. But we need to know whether the section is note section to deal with it.

I'm not sure I follow. Are you saying you need information from the note section to disassemble other sections? Or are you saying you need it to disassemble the note section? If the former, there's already code in the ELFDumper of llvm-readobj for parsing AMDGPU note sections, which you could reuse (it would need moving somewhere outside the llvm-readobj tool into one of the libraries, maybe in the ELFObjectFile stuff, I'm not sure). If the latter, there's still opposition to adding the functionality to the disassembler (the previous concerns haven't been addressed), given that llvm-readobj already provides this functionality.

Jul 15 2020, 12:47 AM · Restricted Project

Jul 14 2020

rochauha added a comment to D83801: [MC] Pass the section to onSymbolStart() for more context.

Can you demonstrate how you are going to use the new interface?

Jul 14 2020, 11:49 PM · Restricted Project
Herald added a project to D83801: [MC] Pass the section to onSymbolStart() for more context: Restricted Project.
Jul 14 2020, 11:34 AM · Restricted Project
Herald added a project to D83776: [AMDGPU] Don't use emitFunctionEntryLabel() from the base AsmPrinter: Restricted Project.
Jul 14 2020, 7:43 AM · Restricted Project

Jul 13 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 13 2020, 3:03 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Changes as per review by @jhenderson.

Jul 13 2020, 2:55 AM · Restricted Project

Jul 7 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 7 2020, 7:43 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Return MCDisassembler::Fail for code object v2.
  • Add missing full stops in doxygen comments.
Jul 7 2020, 7:42 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Handled default statement to silence the warning.
  • Expanded comments for decodeCOMPUTE_PGM_RSRC1 and decodeCOMPUTE_PGM_RSRC2.
  • Removed extra comment at the end of functions.
  • Changed SoftFail to Success for code object v2.
  • Replaced the old test case with a small assembly file.
Jul 7 2020, 7:28 AM · Restricted Project

Jul 6 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 6 2020, 5:07 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Compute .amdhsa_next_free_vgpr based on inverse of what the assembler does to compute GRANULATED_WORKITEM_VGPR_COUNT.
  • Some changes to accomodate differences between GFX9 and GFX10
  • Updated test case for GFX10 as well
Jul 6 2020, 4:58 AM · Restricted Project

Jul 3 2020

rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Size = 64 regardless of success or failure.

Jul 3 2020, 1:35 AM · Restricted Project
rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 3 2020, 1:03 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Fixed code-object-v3 lit test failure introduced in the previous change to this patch.
  • More changes as per inline comments.
Jul 3 2020, 1:03 AM · Restricted Project

Jul 2 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 2 2020, 5:20 AM · Restricted Project
rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 2 2020, 5:20 AM · Restricted Project
rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jul 2 2020, 5:20 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Used macro to shorten printing directives
  • Replaced "\n" with '\n'
  • Removed unnecessary bit shifts for bits that must be 0
  • Removed extra comments for bits that must be 0
Jul 2 2020, 5:20 AM · Restricted Project
rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Updating the code bit by bit based on comments by @scott.linder.

Jul 2 2020, 4:15 AM · Restricted Project

Jun 30 2020

rochauha added a comment to D82858: [llvm-objdump] Detect note section for ELF objects.

I'd also like to point out another fact. There is already some feature overlap between llvm-readobj and llvm-objdump - like printing symbol information using --symbols and --syms respectively. Another such example is using the flag --section-headers in both tools to print section headers.

Jun 30 2020, 11:25 PM · Restricted Project
rochauha added a comment to D82858: [llvm-objdump] Detect note section for ELF objects.
  1. Having multiple tools to do the same job is not a good idea - each requires its own maintenance, the behaviour can diverge, bugs might require fixing in two places/support for new things etc etc etc. In an ideal world, we'd merge all the binary tools (GNU and LLVM) into a single tool, or redistribute functionality somehow, so that we don't have duplicate functionality like we already do. This takes us further away from that ideal.

I agree that having a single tool is the direction we must aim for. But to do so, one tool needs to be improved to the point that it is 'feature complete'. llvm-objdump already disassembles all contents of the binary. It's just that everything is disassembled as instructions. Even notes are disassembled as instructions today. I am not 'adding' anything new; just trying to 'correct' the existing output. Targets will still need to do implement things from their side(if needed) to take advantages of the infrastructure changes.
The initial plan would be to have note record handling in the MC layer. llvm-objdump will just iterate over the notes section. For each note record it will query the registered targets. The owning target will appropriately disassemble the bytes. A note record must be disassembled using the .byte directive if no target owns the note / printing for a particular kind of note is not implemented.

Jun 30 2020, 11:25 PM · Restricted Project
rochauha added inline comments to D82858: [llvm-objdump] Detect note section for ELF objects.
Jun 30 2020, 4:51 AM · Restricted Project
rochauha added a comment to D82858: [llvm-objdump] Detect note section for ELF objects.

Could you more clearly clarify what the motivation here is? Is this working towards some missing GNU compatibility or similar? If so, could you paste an example of what GNU objdump produces, please.

Note that .note sections can be dumped using llvm-readelf in GNU style, just not as part of the disassembly.

Jun 30 2020, 4:51 AM · Restricted Project
rochauha created D82858: [llvm-objdump] Detect note section for ELF objects.
Jun 30 2020, 4:18 AM · Restricted Project

Jun 29 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jun 29 2020, 7:01 AM · Restricted Project
rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jun 29 2020, 5:54 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Added new test case.

Jun 29 2020, 2:39 AM · Restricted Project

Jun 26 2020

rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Following tests fail:

LLVM :: CodeGen/AMDGPU/call-encoding.ll
LLVM :: CodeGen/AMDGPU/s_code_end.ll
LLVM :: MC/AMDGPU/branch-comment.s
LLVM :: MC/AMDGPU/data.s
LLVM :: MC/AMDGPU/labels-branch-gfx9.s
LLVM :: MC/AMDGPU/labels-branch.s
LLVM :: MC/AMDGPU/offsetbug_once.s
LLVM :: MC/AMDGPU/offsetbug_one_and_one.s
LLVM :: MC/AMDGPU/offsetbug_twice.s
LLVM :: MC/AMDGPU/s_endpgm.s
LLVM :: Object/AMDGPU/objdump.s
LLVM :: tools/llvm-cov/ignore-filename-regex.test
LLVM :: tools/llvm-objdump/ELF/AMDGPU/source-lines.ll

Jun 26 2020, 5:24 AM · Restricted Project
rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

The problem is that you're trying to do it all at once. There's no need to implement the full disassembly at once. You can do it in a series of patches, one after the other that build towards the primary goal. For example, there are many if (<X is some value>) type cases, which you could omit - just assume those are all false, in earlier versions, and add them in (with corresponding testing) in a later patch. Similarly, you could assume that all results of x & y return some specific value, e.g. 0, and just print that for now. Yes, that means you won't support everything from the point at which this patch lands, but it will make each individual patch easier to reason with. This fits much better with LLVM's preferred approach - please see https://llvm.org/docs/DeveloperPolicy.html#incremental-development.

Jun 26 2020, 5:24 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Updated to use Cursor. Now there isn't any neet to maintain CurrentIndex.
  • Other small changes related to coding conventions.
Jun 26 2020, 5:24 AM · Restricted Project

Jun 23 2020

rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Minor change to the comment about Size.

Jun 23 2020, 4:12 AM · Restricted Project
rochauha added a comment to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

No idea about the functional logic of this code, but I do wonder whether you'd be better off dividing it into smaller patches for testability.

Jun 23 2020, 4:12 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Made changes based on reviews by @madhur13490 and @jhenderson.

  • Reverse the order of function definitions.
  • std::string => StringRef.
  • std::stringstream => raw_string_ostream.
  • Full stops for comments.
  • Set AddressSize = 8.
  • Remove error handling when reading bytes with DataExtractor since we already check for Bytes.size() == 64 beforehand.
Jun 23 2020, 3:40 AM · Restricted Project

Jun 21 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jun 21 2020, 1:14 PM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Removed the commented code.

Jun 21 2020, 1:14 PM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.

Used enums defined in AMDHSAKernelDescriptor.h

Jun 21 2020, 1:01 AM · Restricted Project

Jun 20 2020

rochauha added inline comments to D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
Jun 20 2020, 3:40 AM · Restricted Project
rochauha updated the diff for D80713: [AMDGPU] Support disassembly for AMDGPU kernel descriptors.
  • Changes due to previous review
  • Changes related to handling GRANULATED_WAVEFRONT_SGPR_COUNT
Jun 20 2020, 2:36 AM · Restricted Project

Jun 18 2020

rochauha committed rG5bd33de9c898: [MC] Pass the symbol rather than its name to onSymbolStart() (authored by rochauha).
[MC] Pass the symbol rather than its name to onSymbolStart()
Jun 18 2020, 9:16 PM
rochauha closed D82090: [MC] Pass the symbol rather than its name to onSymbolStart().
Jun 18 2020, 9:16 PM · Restricted Project
rochauha created D82090: [MC] Pass the symbol rather than its name to onSymbolStart().
Jun 18 2020, 6:29 AM · Restricted Project

Jun 17 2020

rochauha committed rG37e54ffa5059: Revert 'This is a test commit - ded57e1a06a6ba (authored by rochauha).
Revert 'This is a test commit - ded57e1a06a6ba
Jun 17 2020, 12:57 PM
rochauha committed rGded57e1a06a6: This is a test commit (authored by rochauha).
This is a test commit
Jun 17 2020, 12:57 PM

Jun 12 2020

rochauha updated the diff for D80512: [MC] Changes to help improve target specific symbol disassembly.

Minor changes as per review by @scott.linder.

Jun 12 2020, 2:08 AM · Restricted Project

Jun 8 2020

rochauha added a comment to D80512: [MC] Changes to help improve target specific symbol disassembly.

Ping.

Jun 8 2020, 10:37 PM · Restricted Project

Jun 3 2020

rochauha updated the diff for D80512: [MC] Changes to help improve target specific symbol disassembly.

Run git-clang-format.

Jun 3 2020, 10:58 AM · Restricted Project
rochauha updated the diff for D80512: [MC] Changes to help improve target specific symbol disassembly.

To have round trippable disassembly, we fall back to decoding the
remaining bytes as instructions.

Jun 3 2020, 10:25 AM · Restricted Project