OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

aco: fix p_bpermute_gfx6's exec save/restore with wave32

Browse Source 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24693>
This commit is contained in:
Rhys Perry
2023-08-15 11:45:01 +01:00
parent 85957dd6e5
commit 8a024c985f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/amd/compiler/aco_lower_to_hw_instr.cpp
View File

@@ -1093,7 +1093,7 @@ emit_gfx6_bpermute(Program* program, aco_ptr<Instruction>& instr, Builder& bld)
assert(input.physReg() != dst.physReg());
/* Save original EXEC */
bld.sop1(aco_opcode::s_mov_b64, temp_exec, Operand(exec, s2));
bld.sop1(Builder::s_mov, temp_exec, Operand(exec, bld.lm));
/* An "unrolled loop" that is executed per each lane.
* This takes only a few instructions per lane, as opposed to a "real" loop
@@ -1108,7 +1108,7 @@ emit_gfx6_bpermute(Program* program, aco_ptr<Instruction>& instr, Builder& bld)
/* On the active lane, move the data we read from lane N to the destination VGPR */
bld.vop1(aco_opcode::v_mov_b32, dst, Operand(vcc, s1));
/* Restore original EXEC */
bld.sop1(aco_opcode::s_mov_b64, Definition(exec, s2), Operand(temp_exec.physReg(), s2));
bld.sop1(Builder::s_mov, Definition(exec, bld.lm), Operand(temp_exec.physReg(), bld.lm));
}
/* RA assumes that the result is always in the low part of the register, so we have to shift,