From: Tom Stellard <thomas.stell...@amd.com>
We need to include the number of LDS bytes allocated by the state tracker.
---
src/gallium/drivers/radeonsi/radeonsi_compute.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/src/gallium/drivers/radeonsi/radeonsi_compute.c
b/src/gallium/drivers/radeonsi/radeonsi_compute.c
index 10309ba..1adb32f 100644
--- a/src/gallium/drivers/radeonsi/radeonsi_compute.c
+++ b/src/gallium/drivers/radeonsi/radeonsi_compute.c
@@ -191,7 +191,13 @@ static void radeonsi_launch_grid(
| S_00B84C_TGID_Z_EN(1)
| S_00B84C_TG_SIZE_EN(1)
| S_00B84C_TIDIG_COMP_CNT(2)
- | S_00B84C_LDS_SIZE(shader->lds_size)
+ /* XXX: We are over allocating LDS. The shader reports LDS in
+ * blocks of 256 bytes, so if there are 4 bytes lds allocated in
+ * the shader and 4 bytes allocated by the state tracker, then
+ * we will set LDS_SIZE to 512 bytes rather than 256.
+ */
+ | S_00B84C_LDS_SIZE(shader->lds_size +
+ (align(program->local_size, 256) >> 8) + 1)
| S_00B84C_EXCP_EN(0))
;
si_pm4_set_reg(pm4, R_00B854_COMPUTE_RESOURCE_LIMITS, 0);
--
1.8.1.5
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
