[Mesa-dev] [PATCH 4/4] nir: add ARB_shader_ballot and ARB_shader_group_vote instructions

[Connor Abbott]

Signed-off-by: Connor Abbott <cwabbott0 at gmail.com>
---
 src/compiler/nir/nir_intrinsics.h | 14 ++++++++++++++
 src/compiler/nir/nir_opcodes.py   | 18 ++++++++++++++++--
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/src/compiler/nir/nir_intrinsics.h b/src/compiler/nir/nir_intrinsics.h
index 21e7d90..157df7f 100644
--- a/src/compiler/nir/nir_intrinsics.h
+++ b/src/compiler/nir/nir_intrinsics.h
@@ -330,6 +330,20 @@ SYSTEM_VALUE(channel_num, 1, 0, xx, xx, xx)
 SYSTEM_VALUE(alpha_ref_float, 1, 0, xx, xx, xx)
 SYSTEM_VALUE(layer_id, 1, 0, xx, xx, xx)
 SYSTEM_VALUE(view_index, 1, 0, xx, xx, xx)
+SYSTEM_VALUE(subgroup_invocation, 1, 0, xx, xx, xx)
+
+
+/* ARB_shader_ballot instructions */
+
+SYSTEM_VALUE(subgroup_eq_mask, 1, 0, xx, xx, xx)
+SYSTEM_VALUE(subgroup_ge_mask, 1, 0, xx, xx, xx)
+SYSTEM_VALUE(subgroup_gt_mask, 1, 0, xx, xx, xx)
+SYSTEM_VALUE(subgroup_le_mask, 1, 0, xx, xx, xx)
+SYSTEM_VALUE(subgroup_lt_mask, 1, 0, xx, xx, xx)
+
+INTRINSIC(ballot, 1, ARR(0), true, 0, 0, 0, xx, xx, xx,
+          NIR_INTRINSIC_CAN_ELIMINATE | NIR_INTRINSIC_CAN_REORDER |
+          NIR_INTRINSIC_CROSS_THREAD)
 
 /* Blend constant color values.  Float values are clamped. */
 SYSTEM_VALUE(blend_const_color_r_float, 1, 0, xx, xx, xx)
diff --git a/src/compiler/nir/nir_opcodes.py b/src/compiler/nir/nir_opcodes.py
index be3ab6d..05a80b2 100644
--- a/src/compiler/nir/nir_opcodes.py
+++ b/src/compiler/nir/nir_opcodes.py
@@ -120,8 +120,10 @@ def opcode(name, output_size, output_type, input_sizes, input_types,
                           input_types, convergent, cross_thread,
                           algebraic_properties, const_expr)
 
-def unop_convert(name, out_type, in_type, const_expr):
-   opcode(name, 0, out_type, [0], [in_type], "", const_expr)
+def unop_convert(name, out_type, in_type, const_expr, cross_thread=False,
+                 convergent=False):
+   opcode(name, 0, out_type, [0], [in_type], "", const_expr, convergent,
+          cross_thread)
 
 def unop(name, ty, const_expr, convergent=False, cross_thread=False):
    opcode(name, 0, ty, [0], [ty], "", const_expr, convergent, cross_thread)
@@ -355,6 +357,18 @@ for i in xrange(1, 5):
    for j in xrange(1, 5):
       unop_horiz("fnoise{0}_{1}".format(i, j), i, tfloat, j, tfloat, "0.0f")
 
+# ARB_shader_ballot instructions
+
+opcode("read_invocation", 0, tuint, [0, 1], [tuint, tuint32], "", "src0",
+        cross_thread=True)
+unop("read_first_invocation", tuint, "src0", cross_thread=True)
+
+# ARB_shader_group_vote instructions
+
+unop("any_invocations", tbool, "src0", cross_thread=True)
+unop("all_invocations", tbool, "src0", cross_thread=True) 
+unop("all_invocations_equal", tbool, "true", cross_thread=True)
+
 def binop_convert(name, out_type, in_type, alg_props, const_expr):
    opcode(name, 0, out_type, [0, 0], [in_type, in_type], alg_props, const_expr)
 
-- 
2.9.3