https://bugs.freedesktop.org/show_bug.cgi?id=65822
Priority: medium Bug ID: 65822 Assignee: dri-devel@lists.freedesktop.org Summary: [radeonsi] OpenCL is broken Severity: normal Classification: Unclassified OS: Linux (All) Reporter: mustrumr97@gmail.com Hardware: x86-64 (AMD64) Status: NEW Version: git Component: Drivers/Gallium/radeonsi Product: Mesa
Created attachment 80907 --> https://bugs.freedesktop.org/attachment.cgi?id=80907&action=edit Test results
I've attached test results.
a[i]=i+1 b[i]=2*a[i] Test 1: add uints and divide by 3 Test 2: test 1 done 10 times in a for loop Test 3: divide uints Test 4: if statement dependent on load with an addition in the false branch.
Test 1 works, tests 2 and 3 halt and test 4 crashes.
https://bugs.freedesktop.org/show_bug.cgi?id=65822
--- Comment #1 from Tom Stellard tstellar@gmail.com --- I will take a look at this when I get a chance. In the mean time it would be great if you could convert these into piglit tests. Here is a good example: http://cgit.freedesktop.org/piglit/tree/tests/cl/program/execute/sha256-Ch.c...
Probably one file for each test would be good.
https://bugs.freedesktop.org/show_bug.cgi?id=65822
--- Comment #2 from Aaron Watry awatry@gmail.com --- Created attachment 80967 --> https://bugs.freedesktop.org/attachment.cgi?id=80967&action=edit Test Code from initial post converted to piglit tests
I've taken a shot at converting the original tests to piglit tests.
I'll test a radeon 7850 in a bit, but I know that Cedar (radeon 5400, so evergreen) also fails each of these tests (and I got a GPU hang running the uint div test after 6-7 times).
https://bugs.freedesktop.org/show_bug.cgi?id=65822
--- Comment #3 from Aaron Watry awatry@gmail.com --- Created attachment 80969 --> https://bugs.freedesktop.org/attachment.cgi?id=80969&action=edit Shader dumps from a radeon 7850 for test cases in attachment 80967
https://bugs.freedesktop.org/show_bug.cgi?id=65822
Tom Stellard tstellar@gmail.com changed:
What |Removed |Added ---------------------------------------------------------------------------- Attachment #80967|0 |1 is obsolete| | Attachment #80969|0 |1 is obsolete| |
--- Comment #4 from Tom Stellard tstellar@gmail.com --- Created attachment 81026 --> https://bugs.freedesktop.org/attachment.cgi?id=81026&action=edit Updated piglit tests
Thanks for writing the piglit tests, I noticed a few bugs in them though. First, the output argument for all of the tests should be index 2 and not index 0 and second, in test #2 the buffer index should be multiplied by 8 instead of 10. I've fixed the piglit tests in the attached patch and also replaced the '_' with '-' in the filename. The updated tests pass on my Llano APU.
https://bugs.freedesktop.org/show_bug.cgi?id=65822
--- Comment #5 from Aaron Watry awatry@gmail.com --- Ack! You're right. I'm so used to the output being arg 0 from every other piglit test that I neglected to check these.
With that and the index multiplier changed, these tests also pass on Cedar.
All of the test cases currently pass on my pitcairn, except for the code-in-else test, which fails with:
cl-program-tester: /home/awatry/src/llvm/include/llvm/Target/TargetRegisterInfo.h:560: const llvm::TargetRegisterClass* llvm::TargetRegisterInfo::getRegClass(unsigned int) const: Assertion `i < getNumRegClasses() && "Register Class ID out of range"' failed. Stack dump: 0. Running pass 'Function Pass Manager' on module 'radeon'. 1. Running pass 'AMDGPU DAG->DAG Pattern Instruction Selection' on function '@test4'
I'll attach the assembly in a follow-up
https://bugs.freedesktop.org/show_bug.cgi?id=65822
--- Comment #6 from Aaron Watry awatry@gmail.com --- Created attachment 81042 --> https://bugs.freedesktop.org/attachment.cgi?id=81042&action=edit code-in-else.ll
https://bugs.freedesktop.org/show_bug.cgi?id=65822
Tom Stellard tstellar@gmail.com changed:
What |Removed |Added ---------------------------------------------------------------------------- Status|NEW |RESOLVED Resolution|--- |FIXED
--- Comment #7 from Tom Stellard tstellar@gmail.com --- This test case is working for me now. Please re-open if you are still having problems.
dri-devel@lists.freedesktop.org