nir/lower_double_ops: lower floor()

At least i965 hardware does not have native support for floor on doubles.

v2 (Sam):
  - Improve the lowering pass to remove one bcsel (Jason)

Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>

diff --git a/src/compiler/nir/nir.h b/src/compiler/nir/nir.h
index 4a49d6e1ac81c1ba3fe8b313dee6c5509ed7d174..809e83b7d128ada8b71e70ee237c5b7b3ec48b7a 100644 (file)
--- a/src/compiler/nir/nir.h
+++ b/src/compiler/nir/nir.h
@@ -2418,6 +2418,7 @@ typedef enum {
    nir_lower_dsqrt = (1 << 1),
    nir_lower_drsq = (1 << 2),
    nir_lower_dtrunc = (1 << 3),
+   nir_lower_dfloor = (1 << 4),
 } nir_lower_doubles_options;
 
 void nir_lower_doubles(nir_shader *shader, nir_lower_doubles_options options);

diff --git a/src/compiler/nir/nir_lower_double_ops.c b/src/compiler/nir/nir_lower_double_ops.c
index e8ae884d12c10cfd3f2ed8806234a74e01f23e35..1370ddf9266fbba86d68dd45a61f85f450dd6748 100644 (file)
--- a/src/compiler/nir/nir_lower_double_ops.c
+++ b/src/compiler/nir/nir_lower_double_ops.c
@@ -351,6 +351,23 @@ lower_trunc(nir_builder *b, nir_ssa_def *src)
                                                      nir_iand(b, mask_hi, src_hi))));
 }
 
+static nir_ssa_def *
+lower_floor(nir_builder *b, nir_ssa_def *src)
+{
+   /*
+    * For x >= 0, floor(x) = trunc(x)
+    * For x < 0,
+    *    - if x is integer, floor(x) = x
+    *    - otherwise, floor(x) = trunc(x) - 1
+    */
+   nir_ssa_def *tr = nir_ftrunc(b, src);
+   nir_ssa_def *positive = nir_fge(b, src, nir_imm_double(b, 0.0));
+   return nir_bcsel(b,
+                    nir_ior(b, positive, nir_feq(b, src, tr)),
+                    tr,
+                    nir_fsub(b, tr, nir_imm_double(b, 1.0)));
+}
+
 static void
 lower_doubles_instr(nir_alu_instr *instr, nir_lower_doubles_options options)
 {
@@ -379,6 +396,11 @@ lower_doubles_instr(nir_alu_instr *instr, nir_lower_doubles_options options)
          return;
       break;
 
+   case nir_op_ffloor:
+      if (!(options & nir_lower_dfloor))
+         return;
+      break;
+
    default:
       return;
    }
@@ -405,6 +427,9 @@ lower_doubles_instr(nir_alu_instr *instr, nir_lower_doubles_options options)
    case nir_op_ftrunc:
       result = lower_trunc(&bld, src);
       break;
+   case nir_op_ffloor:
+      result = lower_floor(&bld, src);
+      break;
    default:
       unreachable("unhandled opcode");
    }