Mesa (master): nir: improve divergence analysis for loads with non-uniform resources

[GitLab Mirror]

Module: Mesa
Branch: master
Commit: d1283083eac00c6466a0f066df732699b7074c6f
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=d1283083eac00c6466a0f066df732699b7074c6f

Author: Rhys Perry <pendingchaos02 at gmail.com>
Date:   Fri May 22 13:39:06 2020 +0100

nir: improve divergence analysis for loads with non-uniform resources

If ACCESS_NON_UNIFORM is not specified, we can assume the resource is
uniform. This requires nir_lower_non_uniform_access to remove that flag.

A few Detroit: Become Human shaders use a index sourced from a fragment
input which is expected to be uniform.

shader-db (Navi):
Totals from 8 (0.01% of 127638) affected shaders:
SGPRs: 224 -> 384 (+71.43%)
VGPRs: 208 -> 112 (-46.15%)
CodeSize: 5360 -> 5344 (-0.30%); split: -1.49%, +1.19%
Instrs: 1036 -> 1028 (-0.77%); split: -1.93%, +1.16%
VMEM: 1320 -> 608 (-53.94%)
SMEM: 384 -> 336 (-12.50%); split: +14.58%, -27.08%
VClause: 24 -> 16 (-33.33%)
SClause: 48 -> 56 (+16.67%)
PreSGPRs: 124 -> 216 (+74.19%)
PreVGPRs: 168 -> 88 (-47.62%)

Signed-off-by: Rhys Perry <pendingchaos02 at gmail.com>
Reviewed-by: Daniel Schürmann <daniel at schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5201>

---

 src/compiler/nir/nir_divergence_analysis.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/src/compiler/nir/nir_divergence_analysis.c b/src/compiler/nir/nir_divergence_analysis.c
index 98392b97b3c..f148c09e678 100644
--- a/src/compiler/nir/nir_divergence_analysis.c
+++ b/src/compiler/nir/nir_divergence_analysis.c
@@ -241,6 +241,20 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
       break;
    }
 
+   case nir_intrinsic_load_ubo:
+   case nir_intrinsic_load_ssbo:
+      is_divergent = (instr->src[0].ssa->divergent && (nir_intrinsic_access(instr) & ACCESS_NON_UNIFORM)) ||
+                     instr->src[1].ssa->divergent;
+      break;
+
+   case nir_intrinsic_image_load:
+   case nir_intrinsic_image_deref_load:
+   case nir_intrinsic_bindless_image_load:
+      is_divergent = (instr->src[0].ssa->divergent && (nir_intrinsic_access(instr) & ACCESS_NON_UNIFORM)) ||
+                     instr->src[1].ssa->divergent || instr->src[2].ssa->divergent || instr->src[3].ssa->divergent;
+      break;
+
+
    /* Intrinsics with divergence depending on sources */
    case nir_intrinsic_ballot_bitfield_extract:
    case nir_intrinsic_ballot_find_lsb:
@@ -254,8 +268,6 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
    case nir_intrinsic_quad_swap_vertical:
    case nir_intrinsic_quad_swap_diagonal:
    case nir_intrinsic_load_deref:
-   case nir_intrinsic_load_ubo:
-   case nir_intrinsic_load_ssbo:
    case nir_intrinsic_load_shared:
    case nir_intrinsic_load_global:
    case nir_intrinsic_load_global_constant:
@@ -264,9 +276,6 @@ visit_intrinsic(nir_shader *shader, nir_intrinsic_instr *instr)
    case nir_intrinsic_load_constant:
    case nir_intrinsic_load_sample_pos_from_id:
    case nir_intrinsic_load_kernel_input:
-   case nir_intrinsic_image_load:
-   case nir_intrinsic_image_deref_load:
-   case nir_intrinsic_bindless_image_load:
    case nir_intrinsic_image_samples:
    case nir_intrinsic_image_deref_samples:
    case nir_intrinsic_bindless_image_samples: