fix: properly handle hot loop count in aquant pipeline

This commit is contained in:
Erwin Terpstra
2025-11-28 11:55:25 +00:00
parent 0f3806661a
commit 5d4a91a09b

View File

@@ -319,6 +319,8 @@ struct AQuantGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<Prob
if constexpr(HasHotLoop)
{
constexpr index_t tail_count =
((TailNum == TailNumber::Full) || (TailNum == TailNumber::Odd)) ? 1 : 2;
index_t i = 0;
do
{
@@ -366,7 +368,7 @@ struct AQuantGemmPipelineAgBgCrCompV3 : public BaseGemmPipelineAgBgCrCompV3<Prob
__builtin_amdgcn_sched_barrier(0);
i += 1;
} while(i < (num_loop - 1));
} while(i < (num_loop - tail_count));
}
// tail
if constexpr((TailNum == TailNumber::Full) || (TailNum == TailNumber::Odd))