i965: Fix shared local memory size for Gen9+.

Skylake changes the representation of shared local memory size:

 Size   | 0 kB | 1 kB | 2 kB | 4 kB | 8 kB | 16 kB | 32 kB | 64 kB |
 -------------------------------------------------------------------
 Gen7-8 |    0 | none | none |    1 |    2 |     4 |     8 |    16 |
 -------------------------------------------------------------------
 Gen9+  |    0 |    1 |    2 |    3 |    4 |     5 |     6 |     7 |

The old formula would substantially underallocate the amount of space.
This fixes GPU hangs on Skylake when running with full thread counts.

v2: Fix the Vulkan driver too, use a helper function, and fix the table
    in the comments and commit message.

Cc: "12.0" <[email protected]>
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
Reviewed-by: Jordan Justen <[email protected]>

1 files changed, 1 insertions, 9 deletions

diff --git a/src/intel/vulkan/gen8_cmd_buffer.c b/src/intel/vulkan/gen8_cmd_buffer.c
index 1fdc7d29ea0..df4036acbd4 100644
--- a/src/intel/vulkan/gen8_cmd_buffer.c
+++ b/src/intel/vulkan/gen8_cmd_buffer.c
@@ -326,15 +326,7 @@ flush_compute_descriptor_set(struct anv_cmd_buffer *cmd_buffer)
       }
    }
 
-   assert(prog_data->total_shared <= 64 * 1024);
-   uint32_t slm_size = 0;
-   if (prog_data->total_shared > 0) {
-      /* slm_size is in 4k increments, but must be a power of 2. */
-      slm_size = 4 * 1024;
-      while (slm_size < prog_data->total_shared)
-         slm_size <<= 1;
-      slm_size /= 4 * 1024;
-   }
+   const uint32_t slm_size = encode_slm_size(GEN_GEN, prog_data->total_shared);
 
    struct anv_state state =
       anv_state_pool_emit(&device->dynamic_state_pool,