intel: fix the gen 12 compute shader scratch IDs

This is the same idea as "intel: fix the gen 11 compute shader scratch
IDs".

The number of EUs on TGL is not the same as ICL, but the
MEDIA_VFE_STATE restrictions stay the same, so adapt the code to it.
Also, consider the base configuration instead of what we read from the
Kernel.

According to Mark, this fixes the following piglit tests on TGL:

    piglit.spec.arb_compute_shader.execution.shared-atomicmax-uint.tglm64
    piglit.spec.arb_compute_shader.execution.shared-atomicmax-int.tglm64
    piglit.spec.intel_shader_atomic_float_minmax.execution.shared-atomicmax-float.tglm64

v2: s/ICL+/Gen11+/ (Jason).

Cc: mesa-stable@lists.freedesktop.org
Tested-by: Mark Janes <mark.a.janes@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4006>

diff --git a/src/gallium/drivers/iris/iris_program.c b/src/gallium/drivers/iris/iris_program.c
index 701cfa20aea4362fd217b19ee5687ee113f2e9e8..d7e470b4238cd5c85b35d836b4a20cf4b3d626b0 100644 (file)
--- a/src/gallium/drivers/iris/iris_program.c
+++ b/src/gallium/drivers/iris/iris_program.c
@@ -2054,11 +2054,13 @@ iris_get_scratch_space(struct iris_context *ice,
     *
     * This hack is no longer necessary on Gen11+.
     *
-    * For, ICL, scratch space allocation is based on the number of threads
+    * For, Gen11+, scratch space allocation is based on the number of threads
     * in the base configuration.
     */
    unsigned subslice_total = screen->subslice_total;
-   if (devinfo->gen == 11)
+   if (devinfo->gen >= 12)
+      subslice_total = devinfo->num_subslices[0];
+   else if (devinfo->gen == 11)
       subslice_total = 8;
    else if (devinfo->gen < 11)
       subslice_total = 4 * devinfo->num_slices;
@@ -2067,7 +2069,10 @@ iris_get_scratch_space(struct iris_context *ice,
    if (!*bop) {
       unsigned scratch_ids_per_subslice = devinfo->max_cs_threads;
 
-      if (devinfo->gen >= 11) {
+      if (devinfo->gen >= 12) {
+         /* Same as ICL below, but with 16 EUs. */
+         scratch_ids_per_subslice = 16 * 8;
+      } else if (devinfo->gen == 11) {
          /* The MEDIA_VFE_STATE docs say:
           *
           *    "Starting with this configuration, the Maximum Number of

diff --git a/src/intel/vulkan/anv_allocator.c b/src/intel/vulkan/anv_allocator.c
index 112a12014cb846740ff723c74b808f364fbd154f..f698289155bd54b5e721960dd4986a3567438e04 100644 (file)
--- a/src/intel/vulkan/anv_allocator.c
+++ b/src/intel/vulkan/anv_allocator.c
@@ -1397,13 +1397,18 @@ anv_scratch_pool_alloc(struct anv_device *device, struct anv_scratch_pool *pool,
 
    unsigned subslices = MAX2(device->physical->subslice_total, 1);
 
-   /* For, ICL, scratch space allocation is based on the number of threads
+   /* For, Gen11+, scratch space allocation is based on the number of threads
     * in the base configuration. */
-   if (devinfo->gen == 11)
+   if (devinfo->gen >= 12)
+      subslices = devinfo->num_subslices[0];
+   else if (devinfo->gen == 11)
       subslices = 8;
 
    unsigned scratch_ids_per_subslice;
-   if (devinfo->gen >= 11) {
+   if (devinfo->gen >= 12) {
+      /* Same as ICL below, but with 16 EUs. */
+      scratch_ids_per_subslice = 16 * 8;
+   } else if (devinfo->gen == 11) {
       /* The MEDIA_VFE_STATE docs say:
        *
        *    "Starting with this configuration, the Maximum Number of