Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix uninitialized f0 and re-enable sm75/sm86/sm89 #120

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+6 −5
Open

Fix uninitialized f0 and re-enable sm75/sm86/sm89 #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
80a1860
fix: uninitialized f0
lucifer1004 Apr 12, 2024
c8ba48d
Merge branch 'main' into feature/warp
ysyecust Apr 28, 2024
855258f
Merge branch 'main' into feature/warp
ysyecust May 15, 2024
133ea1b
Merge branch 'main' into feature/warp
ysyecust Jul 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 4 additions & 3 deletions unidock/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,10 @@ if(NOT DEFINED CMAKE_CUDA_ARCHITECTURES)
# https://en.wikipedia.org/wiki/CUDA#GPUs_supported
set(CMAKE_CUDA_ARCHITECTURES
70 # V100
# 75 # RTX 20, T4
75 # RTX 20, T4
80 # A100, A800
# 86 # RTX 30 89 # RTX 40, L40
86 # RTX 30
89 # RTX 40, L40
90 # H100
)
endif()
Expand Down Expand Up @@ -191,4 +192,4 @@ add_custom_target(
COMMENT "Running clang-format"
VERBATIM)

# >>>>>> Clang Format End
# >>>>>> Clang Format End
4 changes: 2 additions & 2 deletions unidock/src/cuda/warp_ops.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,7 +989,7 @@ __device__ void bfgs_warp(cg::thread_block_tile<TileSize> &tile, output_type_cud
// Profiling: perform timing within kernel
int n = 3 + 3 + x->lig_torsion_size; /* the dimensions of matirx */

float f0, f1, f_orig, alpha;
float f0 = 0.0f, f1, f_orig, alpha;

matrix_d_init_warp(tile, h, n, 0);
matrix_d_set_diagonal_warp(tile, h, 1);
Expand Down Expand Up @@ -1059,7 +1059,7 @@ __device__ void bfgs_warp(cg::thread_block_tile<TileSize> &tile, output_type_cud
// Profiling: perform timing within kernel
int n = 3 + 3 + x->lig_torsion_size; /* the dimensions of matirx */

float f0, f1, f_orig, alpha;
float f0 = 0.0f, f1, f_orig, alpha;

matrix_d_init_warp<TileSize,Config>(tile, h, n, 0);
matrix_d_set_diagonal_warp<TileSize,Config>(tile, h, 1);
Expand Down
Loading