Refactor Vulkan backend to allow multiple contexts (#7961)
* Refactor Vulkan backend to allow multiple contexts * Fix too many shader groups called validation error in llama3 on AMD and Intel GPUs * Fix Vulkan debug build error
This commit is contained in:
parent
b5a5f34efa
commit
45c0e2e4c1
8 changed files with 21021 additions and 20675 deletions
39661
ggml-vulkan-shaders.hpp
39661
ggml-vulkan-shaders.hpp
File diff suppressed because it is too large
Load diff
2023
ggml-vulkan.cpp
2023
ggml-vulkan.cpp
File diff suppressed because it is too large
Load diff
|
@ -13,7 +13,7 @@ layout (constant_id = 0) const uint BLOCK_SIZE = 32;
|
|||
shared FLOAT_TYPE tmp[BLOCK_SIZE];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
const uint tid = gl_LocalInvocationID.x;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
|
|
|
@ -7,7 +7,7 @@ layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
|
|||
shared FLOAT_TYPE tmp[32];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
get_offsets(a_offset, b_offset, d_offset);
|
||||
|
|
|
@ -7,7 +7,7 @@ layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
|
|||
shared FLOAT_TYPE tmp[32];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
get_offsets(a_offset, b_offset, d_offset);
|
||||
|
|
|
@ -7,7 +7,7 @@ layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
|
|||
shared FLOAT_TYPE tmp[32];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
get_offsets(a_offset, b_offset, d_offset);
|
||||
|
|
|
@ -7,7 +7,7 @@ layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
|
|||
shared FLOAT_TYPE tmp[32];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
get_offsets(a_offset, b_offset, d_offset);
|
||||
|
|
|
@ -7,7 +7,7 @@ layout(local_size_x = 32, local_size_y = 1, local_size_z = 1) in;
|
|||
shared FLOAT_TYPE tmp[32];
|
||||
|
||||
void main() {
|
||||
const uint row = gl_WorkGroupID.x;
|
||||
const uint row = gl_WorkGroupID.x + gl_NumWorkGroups.x * gl_WorkGroupID.z;
|
||||
|
||||
uint a_offset, b_offset, d_offset;
|
||||
get_offsets(a_offset, b_offset, d_offset);
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue