I don't remember if we've tried this recently, but does disabling power
containment help?

diff --git a/drivers/gpu/drm/radeon/ni_dpm.c b/drivers/gpu/drm/radeon/ni_dpm.c
index 22c3391..19b7c68 100644
--- a/drivers/gpu/drm/radeon/ni_dpm.c
+++ b/drivers/gpu/drm/radeon/ni_dpm.c
@@ -4250,7 +4250,7 @@ int ni_dpm_init(struct radeon_device *rdev)
                break;
        }

-       if (ni_pi->cac_weights->enable_power_containment_by_default) {
+       if (0/*ni_pi->cac_weights->enable_power_containment_by_default*/) {
                ni_pi->enable_power_containment = true;
                ni_pi->enable_cac = true;
                ni_pi->enable_sq_ramping = true;