Skip to content

Bump tt2 header version #18

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

Closed
rocm-devops wants to merge 2 commits into from
Closed

Bump tt2 header version #18

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a3228c2
Bump tt2 header version
ApoKalipse-V Jul 1, 2025
4341670
Namespace fix
ApoKalipse-V Jul 1, 2025
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
11 changes: 7 additions & 4 deletions src/core/threadtrace.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,10 +74,13 @@ typedef union {
uint32_t raw;
} aqlprofile_att_header_marker_t;

inline att_header_packet_t getHeaderPacket(int SE, int CU, int SIMD) {
inline att_header_packet_t getHeaderPacket(int SE, int CU, int SIMD, aql_profile::gpu_id_t id) {
att_header_packet_t header{.raw = 0};
header.legacy_version = 0x11; // The thread trace viewer only sees gfx9 for 0x11
header.gfx9_version2 = 4;
header.legacy_version = 0x11;
// Requires decoder version 0.1.2 or higher
if(id == aql_profile::MI300_GPU_ID) header.gfx9_version2 = 5;
else if(id == aql_profile::MI350_GPU_ID) header.gfx9_version2 = 6;
else header.gfx9_version2 = 4;
header.SEID = SE;
header.DCU = CU;
header.DSIMDM = SIMD;
Expand Down Expand Up @@ -157,7 +160,7 @@ hsa_status_t _internal_aqlprofile_att_iterate_data(aqlprofile_handle_t handle,
char* sample_data_ptr = (char*)cpu_sample.data();
if (pm4_factory->GetGpuId() < aql_profile::GFX10_GPU_ID) {
auto* header = reinterpret_cast<att_header_packet_t*>(cpu_sample.data());
*header = getHeaderPacket(se_index, target_cu, memorymgr->GetSimdMask());
*header = getHeaderPacket(se_index, target_cu, memorymgr->GetSimdMask(), pm4_factory->GetGpuId());
sample_data_ptr += sizeof(att_header_packet_t);
sample_size_plus_header = sample_size + sizeof(att_header_packet_t);
}
Expand Down