0b03e6b411
[Ventus][fix]Fix missing vmv instruction for FrameReg in divergent path
2024-06-06 16:16:57 +08:00
3fffdc5d16
Merge pull request #115 from THU-DSP-LAB/workitem
...
[VENTUS][fix] Add function sections for workitem functions to reduce binary size
2024-06-04 08:56:25 +08:00
492b35de44
Merge pull request #126 from THU-DSP-LAB/readme
...
[NFC][readme] Modify some compiler flags
2024-06-03 16:48:18 +08:00
zhoujing
3abe6bd242
[NFC][readme] Modify some compiler flags
2024-06-03 16:47:28 +08:00
zhoujing
bdfa4ec6af
[VENTUS][fix] Add function sections for workitem functions
...
Signed-off-by: zhoujing <jing.zhou@terapines.com>
2024-05-31 22:29:05 +08:00
7c78b29815
Merge pull request #122 from THU-DSP-LAB/compress_instruction_disassemble
...
[VENTUS][fix] Disable compress instruction disassemble
2024-05-30 14:38:50 +08:00
76ed2fc9e3
Merge pull request #121 from ziliangzl/vmsle
...
[VENTUS][fix] Fix missing regexti instruction for vmsle instruction
2024-05-23 09:06:58 +08:00
11b55acb48
[VENTUS][fix]Fix missing regext instruction for vmsle instruction
...
This bug caused PseudoVMSLT_VI node didn't insert regext.
Now OPENCL-CTS relationals test passed.
2024-05-21 17:09:48 +08:00
9d966660b6
Merge pull request #116 from ziliangzl/inline-asm
...
[VENTUS][NFC] Add inline assembly codes testcase
2024-05-20 09:43:55 +08:00
c168c442ce
Merge pull request #118 from THU-DSP-LAB/checkInstr
...
[VENTUS][fix] Assign initial value for VastartStoreFrameIndex
2024-05-18 14:17:34 +08:00
60f388930d
[VENTUS][fix]Assign initial value for VastartStoreFrameIndex
...
VastartStoreFrameIndex havn't initial value, caused issue THU-DSP-LAB/llvm-project#117
2024-05-15 13:39:07 +08:00
451062314a
Merge pull request #119 from ziliangzl/workgroup
...
[VENTUS][libclc][feat] Add missing workgroup function implementations
2024-05-15 11:36:10 +08:00
b465e58817
[VENTUS][fix] Add a switch to the C extension
...
Add a switch to the C extension, now the C extension is turned off by default.
2024-05-14 17:26:24 +08:00
6a8e4d4667
[VENTUS][ #119 ]Fix workgroup function barrier scope
2024-05-14 14:03:20 +08:00
d977b0bf8b
[VENTUS][ #119 ]Complete workgroup function implementation
...
Implement work_group_reduce_<op> functions in wgreduce.cl .
Implement work_group_scan_inclusive_<op> work_group_scan_exclusive_<op> functions in wgscan.cl .
Passed corresponding OPENCL-CTS tests.
2024-05-14 13:36:09 +08:00
408ed74df2
[VENTUS][fix] Modify the disassembly result of a compress instruction error
...
Modify the disassembly result of a compress instruction error.
2024-05-13 15:57:55 +08:00
4789f2096b
[VENTUS][ #119 ]Add work_group_broadcast implementation
...
Passed corresponding OPENCL-CTS test.
2024-05-13 11:22:56 +08:00
d63caa094a
[VENTUS][ #119 ]Fix __wg_scratch multiple define
...
1.Global variable shouldn't define in header.
2.Fix code format.
2024-05-13 11:18:03 +08:00
6b70120436
[VENTUS][libclc][feat]Start workgroup function implementation
...
1.Implement barrier and work_group_barrier function with intrinsics.
2.Implement work_group_all and work_group_any function,passed corresponding OPENCL-CTS test.
2024-05-11 16:38:52 +08:00
3267496a27
[VENTUS][NFC]Add inline-asm testcase
...
Add an inline-asm testcase for constraint r
Add an inline-asm testcase for branch instruction
2024-05-07 15:33:42 +08:00
279251d31d
Merge pull request #114 from ziliangzl/compile-guide
...
[VENTUS][NFC] Add compile guide in README
2024-04-29 16:15:33 +08:00
5ff2eddbad
[VENTUS][NFC]Add compile guide in README
...
1. Explained how to generate ELF file step-by-step.
2.Add compile assembly code to object file example.
2024-04-29 16:11:42 +08:00
42a893c3be
Merge pull request #113 from THU-DSP-LAB/workaround
...
[VENTUS][workaround] Fix flw/fsw assembly errors
2024-04-26 16:12:15 +08:00
zhoujing
573ae5e8ee
[VENTUS][workaround] Fix flw/fsw assembly errors
...
Signed-off-by: zhoujing <jing.zhou@terapines.com>
This is just a workarond, when new instruction is added by HW, revert this commit
2024-04-26 15:14:22 +08:00
45856f653d
Merge pull request #112 from ziliangzl/Pseudo-FLW/FSW
...
[VENTUS][fix] Fix FLW/FSW instruction encoding conflict
2024-04-26 13:28:05 +08:00
8be3150696
[ #112 ][fix]Remove flw/fsw InstAlias
...
1.Removed flw/fsw InstAlias for now,cause flw/fsw could not match correctly.
2.Modified kernel_arg testcase.
2024-04-26 10:59:35 +08:00
4354b039f3
[VENTUS][fix]Fix FLW/FSW instruction coding conflict
...
Replace FLW/FSW instruction with PseudoFLW/PseudoFSW
2024-04-25 10:44:57 +08:00
968f0c07cd
Merge pull request #110 from ziliangzl/divergent-analysis
...
[Ventus][NFC] Add kernel function testcase
2024-04-23 14:22:12 +08:00
47a0946abc
[VENTUS][fix]Fix kernel divergent analysis
...
1.Kernel function argument is not divergent
2.GPRF32 is not divergent
3.Set PHINode is divergent
4.Add flw/fsw instruction for GPRF32
5.Add a floating add kernel function test case
2024-04-23 14:07:54 +08:00
1347c06d50
Merge pull request #109 from ziliangzl/divergent-analyse
...
[VENTUS][fix] Fix kernel divergent analysis
2024-04-22 15:58:52 +08:00
d138bdacf6
[VENTUS][fix]Fix kernel divergent analysis
2024-04-22 15:53:36 +08:00
4d31e996d7
Merge pull request #108 from THU-DSP-LAB/mv_after_join
...
[VENTUS][RISCV] Fix move instructions after JOIN move forward bug
2024-04-03 13:06:32 +08:00
f781479b52
[VENTUS][RISCV] Fix move instructions after JOIN move forward bug
...
1. If the move instruction needs to be moved forward, it will only be inserted after the last corresponding move instruction in the predecessor basic block.
2. The first instruction of the predecessor is also counted as a possible insertion point.
2024-03-29 16:15:12 +08:00
078bb26e2e
Merge pull request #106 from THU-DSP-LAB/patch
...
[patch] Add a fix patch from terapines_dev branch
2024-03-11 09:28:55 +08:00
zhoujing
797c85d829
[patch] Add a fix patch from terapines_dev branch
2024-03-08 18:23:47 +08:00
1a36d94fd0
Merge pull request #105 from THU-DSP-LAB/test-case-fix
...
[NFC][fix] Fix test cases failure
2024-03-07 11:06:12 +08:00
zhoujing
9b11eb8feb
[NFC][fix] Fix test cases failure
2024-03-07 10:57:30 +08:00
efef613b61
Merge pull request #83 from THU-DSP-LAB/34_local_addressed_variables_into_stack
...
[VENTUS][fix] Put local variables declared in kernel function into shared memory
2024-03-06 09:19:25 +08:00
45a884a824
Merge pull request #104 from THU-DSP-LAB/fix-insert-vmv
...
[VENTUS][fix] Fix insert vmv instruction bug when vmv instruction is in JOIN MBB
2024-03-05 17:06:42 +08:00
zhoujing
87fe5f3ce8
[VENTUS][fix] Put local variables declared in kernel function into shared memory
2024-03-05 16:32:59 +08:00
zhoujing
a909be0434
[VENTUS][fix] Fix insert vmv instruction bug when vmv instruction is in JOIN MBB
2024-03-05 15:26:43 +08:00
a48f51ab76
Merge pull request #101 from THU-DSP-LAB/resource_manage
...
[VENTUS][fix] Fix ventus resource usage calculation error
2024-03-05 14:16:57 +08:00
292c639510
Merge pull request #103 from THU-DSP-LAB/102-code-refactoring
...
[VENTUS][NFC] Remove dead code and refactor code
2024-03-04 23:01:27 +08:00
1a04073d12
[VENTUS][NFC] Remove dead code and refactor code
...
1. The variable NumRetVGPRs is not used;
2. According to the purpose of function numRegsForType, it is more suitable as
a public member function.
2024-03-04 18:52:01 +08:00
c42c00f67e
[VENTUS][fix] Modified the resource statistics interface
...
1. The origin interface will not be called under the -O0 optimization.
2. New interfaces added to epilogue pass.
2024-03-04 15:44:30 +08:00
ed93af0195
Merge pull request #99 from THU-DSP-LAB/fix-runtime-error
...
[fix] Fix runtime path errors
2024-02-23 15:04:33 +08:00
zhoujing
18f624b661
[VENTUS][fix] Add files to install package && add VENTUS_INSTALL_PREFIX enviroments variable
...
Add VENTUS_INSTALL_PREFIX for runtime use(pocl)
2024-02-23 10:52:28 +08:00
b32b529523
Merge pull request #98 from THU-DSP-LAB/56_workitem_function_fix
...
[VENTUS][fix] Fix workitem function implementation bug
2024-02-01 15:05:25 +08:00
zhoujing
6cac00d141
[NFC] comment fix
2024-02-01 15:03:53 +08:00
4b25812260
[VENTUS] Fix some comments
...
Fix some comments.
2024-02-01 14:56:01 +08:00
ziliangzl
zhoujing