index
:
ZLUDA
better_build
better_inject
blender_42
bpermute
build_fix
build_fixes
build_fixes2
builtin_fixes_try2
carry_fix
cgbn_readme
codegen_variables
compat
cuda-12-4
detours
dump_replay
error_report
feature_matching
fix_build
fix_builtin_wip
geekbench
geekbnch
gh-pages
improve_ci
improve_ci2
kernel_dump
linux_linker_hack
llama2
llvm
malloc_private
master
meshroom
misc_fixes
new_dev
ockl_fix
oidn
older_cuda
parser_rewrite
parser_rewrite_try1
refactor_vectors
regen_tests
remove_sema
repass
repass2
sad_inst
stateful_try1
stateful_try2
sust_suld
troubleshooting_docs
update-readme
update_docs
wave32_report_fix
win_fix
CUDA on AMD GPUs
vosen
about
summary
refs
log
tree
commit
diff
homepage
log msg
author
committer
range
Age
Commit message (
Expand
)
Author
2021-08-08
Additional options to clang
Andrzej Janik
2021-08-08
Explicitly mark input to AMD as bitcode
Andrzej Janik
2021-08-07
Persist AMD kernels for later debug
Andrzej Janik
2021-08-07
Use raw interop for building programs
Andrzej Janik
2021-08-07
Hack to read clang output
Andrzej Janik
2021-08-07
Try seeking before reading
Andrzej Janik
2021-08-07
Take path to llvm-spirv from environment
Andrzej Janik
2021-08-07
Handle xnack suffix in device name
Andrzej Janik
2021-08-07
Fix warnings
Andrzej Janik
2021-08-07
Addd missing file
Andrzej Janik
2021-08-07
Remove L0 from nvml
Andrzej Janik
2021-08-06
Wire up AMD compilation
Andrzej Janik
2021-08-06
Remove all use of L0
Andrzej Janik
2021-08-04
Convert OpenCL host code to SVM
Andrzej Janik
2021-08-03
Hack enough functionality that AMD GPU code builds
Andrzej Janik
2021-08-02
Use calls to OpenCL builtins when translating sregs, do SPIRV->LLVM conversio...
Andrzej Janik
2021-08-01
Change codegen for mul.wide
Andrzej Janik
2021-07-25
Tune generated code, add a workaround for geekbench
Andrzej Janik
2021-07-22
Finish converting to OpenCL
Andrzej Janik
2021-07-21
Start converting to OpenCL
Andrzej Janik
2021-07-06
Synchronize through barrier
Andrzej Janik
2021-07-05
Fix overzealus check
Andrzej Janik
2021-07-05
Fix typo
Andrzej Janik
2021-07-04
Implement stream-wide event reuse
Andrzej Janik
2021-07-04
Use immediate command lists
Andrzej Janik
2021-07-04
Make everything async
Andrzej Janik
2021-07-04
Remember to actually submit workload
Andrzej Janik
2021-07-04
First attempt at async host side
Andrzej Janik
2021-07-03
Regenerate SPIR-V for ptx_impl and fix weird handling of ptr-ptr add or sub
Andrzej Janik
2021-07-02
Be more correct when emitting brev, refactor inst->func call pass
Andrzej Janik
2021-06-30
Allow to set range of dump kernels
Andrzej Janik
2021-06-28
Bunch of tiny fixes and improvements
Andrzej Janik
2021-06-27
Revert "Fix offset calculation in kernel launch"
Andrzej Janik
2021-06-27
Fix bugs related to replay on Linux
Andrzej Janik
2021-06-27
Check for presence of ".version" instead of ".address_size" (which is optional)
Andrzej Janik
2021-06-27
Fix offset calculation in kernel launch
Andrzej Janik
2021-06-27
Fix more bugs
Andrzej Janik
2021-06-27
Add missing import
Andrzej Janik
2021-06-27
Add missing pub qualifier
Andrzej Janik
2021-06-27
Fix build on Linux
Andrzej Janik
2021-06-25
Allow ptr offsets to non-scalar types
Andrzej Janik
2021-06-25
Merge branch 'one_type_type2'
Andrzej Janik
2021-06-25
Clean up warnings
Andrzej Janik
2021-06-25
Update tests
Andrzej Janik
2021-06-20
Prepare level zero and our compiler for global addressing
Andrzej Janik
2021-06-12
Fix problems with non-dereferencing inline addition
Andrzej Janik
2021-06-11
Fix handling of kernel args in stateful conversion
Andrzej Janik
2021-06-11
Slightly improve stateful optimization
Andrzej Janik
2021-06-06
Fix small bug in stateful postprocess
Andrzej Janik
2021-06-06
Make stateful optimization build
Andrzej Janik
[next]