diff options
author | Tim Renouf <tim.renouf@amd.com> | 2025-08-15 16:33:06 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2025-08-15 16:33:06 +0100 |
commit | f279c47cb3e7191a22703b837e006eb7dd591de7 (patch) | |
tree | 5373a7594a460c377d91fd171f7e3753fa244103 /lldb/source/Commands/CommandObjectExpression.cpp | |
parent | 0b04168948d00baf9c656ce02a85dc5cf6703581 (diff) | |
download | llvm-f279c47cb3e7191a22703b837e006eb7dd591de7.zip llvm-f279c47cb3e7191a22703b837e006eb7dd591de7.tar.gz llvm-f279c47cb3e7191a22703b837e006eb7dd591de7.tar.bz2 |
AMDGPU gfx12: Add _dvgpr$ symbols for dynamic VGPRs (#148251)
For each function with the AMDGPU_CS_Chain calling convention, with
dynamic VGPRs enabled, add a _dvgpr$ symbol, with the value of the
function symbol, plus an offset encoding one less than the number of
VGPR blocks used by the function (16 VGPRs per block, no more than 128)
in bits 5..3 of the symbol value. This is used by a front-end to have
functions that are chained rather than called, and a dispatcher that
dynamically resizes the VGPR count before dispatching to a function.
Diffstat (limited to 'lldb/source/Commands/CommandObjectExpression.cpp')
0 files changed, 0 insertions, 0 deletions