Skip to content

Commit

Permalink
Update DBCSR
Browse files Browse the repository at this point in the history
  • Loading branch information
alazzaro committed Dec 23, 2021
1 parent a65146a commit 507a1e5
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion exts/dbcsr
Submodule dbcsr updated 61 files
+2 −2 docs/guide/2-user-guide/1-installation/index.md
+48 −0 docs/guide/2-user-guide/4-gpu/index.md
+3 −3 docs/guide/3-developer-guide/3-programming/1-overview/index.md
+6 −9 docs/guide/3-developer-guide/4-performance/2-just-in-time-compilation.md
+56 −56 examples/dbcsr_example_3.cpp
+1 −1 examples/dbcsr_tensor_example_2.cpp
+1 −0 src/acc/acc.h
+3 −3 src/acc/acc_bench.h
+111 −65 src/acc/acc_bench_smm.c
+1 −1 src/acc/acc_bench_trans.c
+23 −0 src/acc/acc_libsmm.h
+30 −19 src/acc/acc_triplets.sh
+28 −15 src/acc/cuda/Makefile
+4 −3 src/acc/cuda/acc_cuda.cpp
+10 −7 src/acc/cuda/acc_cuda.h
+1 −1 src/acc/cuda/dbcsr_cuda_nvtx_cu.cpp
+3 −3 src/acc/cuda_hip/acc_dev.cpp
+7 −7 src/acc/cuda_hip/acc_error.cpp
+1 −1 src/acc/cuda_hip/acc_error.h
+22 −22 src/acc/cuda_hip/acc_event.cpp
+2 −2 src/acc/cuda_hip/acc_init.cpp
+16 −16 src/acc/cuda_hip/acc_mem.cpp
+8 −8 src/acc/cuda_hip/acc_stream.cpp
+8 −7 src/acc/hip/acc_hip.cpp
+13 −9 src/acc/hip/acc_hip.h
+2 −2 src/acc/libsmm_acc/generate_parameters.py
+1 −3 src/acc/libsmm_acc/kernels/README.md
+1 −1 src/acc/libsmm_acc/kernels/smm_acc_dnt_base.py
+19 −19 src/acc/libsmm_acc/kernels/smm_acc_dnt_largeDB1.h
+15 −15 src/acc/libsmm_acc/kernels/smm_acc_dnt_largeDB2.h
+59 −59 src/acc/libsmm_acc/kernels/smm_acc_dnt_medium.h
+17 −17 src/acc/libsmm_acc/kernels/smm_acc_dnt_small.h
+5 −5 src/acc/libsmm_acc/kernels/smm_acc_dnt_tiny.h
+3 −3 src/acc/libsmm_acc/kernels/smm_acc_transpose.h
+69 −41 src/acc/libsmm_acc/libsmm_acc.cpp
+52 −64 src/acc/libsmm_acc/libsmm_acc_benchmark.cpp
+13 −15 src/acc/libsmm_acc/libsmm_acc_init.cpp
+1 −4 src/acc/libsmm_acc/libsmm_acc_init.h
+1 −1 src/acc/libsmm_acc/parameters_utils.h
+9 −9 src/acc/libsmm_acc/tune/tune_setup.py
+40 −10 src/acc/opencl/Makefile
+414 −184 src/acc/opencl/acc_opencl.c
+32 −13 src/acc/opencl/acc_opencl.h
+2 −2 src/acc/opencl/acc_opencl.sh
+2 −1 src/acc/opencl/acc_opencl_event.c
+42 −15 src/acc/opencl/acc_opencl_mem.c
+59 −10 src/acc/opencl/acc_opencl_stream.c
+2 −2 src/acc/opencl/smm/README.md
+368 −191 src/acc/opencl/smm/kernels/multiply.cl
+2 −2 src/acc/opencl/smm/kernels/transpose.cl
+289 −136 src/acc/opencl/smm/opencl_libsmm.c
+2 −2 src/acc/opencl/smm/opencl_libsmm.h
+216 −98 src/acc/opencl/smm/tune_multiply.py
+112 −44 src/acc/opencl/smm/tune_multiply.sh
+15 −15 src/dbcsr.h
+6 −6 src/tensors/dbcsr_tensor.h
+1 −1 tests/dbcsr_tensor_test.cpp
+171 −181 tests/dbcsr_test.cpp
+9 −9 tests/libsmm_acc_timer_multiply.cpp.template
+3 −3 tests/libsmm_acc_unittest_multiply.cpp.template
+7 −7 tests/libsmm_acc_unittest_transpose.cpp

0 comments on commit 507a1e5

Please sign in to comment.