nvc0: account for shader-allocated local memory needs

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>

diff --git a/src/gallium/drivers/nouveau/nvc0/nvc0_compute.c b/src/gallium/drivers/nouveau/nvc0/nvc0_compute.c
index bbc8edb..2324f36 100644 (file)
--- a/src/gallium/drivers/nouveau/nvc0/nvc0_compute.c
+++ b/src/gallium/drivers/nouveau/nvc0/nvc0_compute.c
@@ -331,7 +331,7 @@ nvc0_launch_grid(struct pipe_context *pipe, const struct pipe_grid_info *info)
    PUSH_DATA (push, nvc0_program_symbol_offset(cp, info->pc));
 
    BEGIN_NVC0(push, NVC0_CP(LOCAL_POS_ALLOC), 3);
-   PUSH_DATA (push, align(cp->cp.lmem_size, 0x10));
+   PUSH_DATA (push, (cp->hdr[1] & 0xfffff0) + align(cp->cp.lmem_size, 0x10));
    PUSH_DATA (push, 0);
    PUSH_DATA (push, 0x800); /* WARP_CSTACK_SIZE */
 

diff --git a/src/gallium/drivers/nouveau/nvc0/nve4_compute.c b/src/gallium/drivers/nouveau/nvc0/nve4_compute.c
index 1fe6026..7334c5f 100644 (file)
--- a/src/gallium/drivers/nouveau/nvc0/nve4_compute.c
+++ b/src/gallium/drivers/nouveau/nvc0/nve4_compute.c
@@ -553,7 +553,7 @@ nve4_compute_setup_launch_desc(struct nvc0_context *nvc0,
    desc->blockdim_z = info->block[2];
 
    desc->shared_size = align(cp->cp.smem_size, 0x100);
-   desc->local_size_p = align(cp->cp.lmem_size, 0x10);
+   desc->local_size_p = (cp->hdr[1] & 0xfffff0) + align(cp->cp.lmem_size, 0x10);
    desc->local_size_n = 0;
    desc->cstack_size = 0x800;
    desc->cache_split = nve4_compute_derive_cache_split(nvc0, cp->cp.smem_size);