nir: add many passes that lower and optimize 16-bit input/outputs and samplers

Added:
* a pass that renumbers bases of IO intrinsics
* a pass that converts mediump IO to 16 bits, optionally using the new
  packed varying slots
* a pass that sets (forces) mediump in IO intrinsics (for testing)
* a pass that remaps VARYING_SLOT_VAR[0..15]_16BIT to VARYING_SLOT_VAR[0..31]
  (if some shader stages don't want packed varyings)
* a pass that folds type conversions around texture opcodes into those
  opcodes (e.g. tex(f2f32(coord), ..) is changed into tex accepting f16)
* a pass that changes (legalizes) sampler src and dst types based on specified
  hw constraints (e.g. derivatives must be the same type as coordinates)

Reviewed-by: Matt Turner <mattst88@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9050>

1 files changed, 19 insertions, 0 deletions

diff --git a/src/util/bitset.h b/src/util/bitset.h
index 29de65e839c..b9e968293b1 100644
--- a/src/util/bitset.h
+++ b/src/util/bitset.h
@@ -80,6 +80,25 @@
    ((x)[BITSET_BITWORD(b)] &= ~BITSET_RANGE(b, e)) : \
    (assert (!"BITSET_CLEAR_RANGE: bit range crosses word boundary"), 0))
 
+static inline unsigned
+__bitset_prefix_sum(const BITSET_WORD *x, unsigned b, unsigned n)
+{
+   unsigned prefix = 0;
+
+   for (unsigned i = 0; i < n; i++) {
+      if ((i + 1) * BITSET_WORDBITS <= b) {
+         prefix += util_bitcount(x[i]);
+      } else {
+         prefix += util_bitcount(x[i] & BITFIELD_MASK(b - i * BITSET_WORDBITS));
+         break;
+      }
+   }
+   return prefix;
+}
+
+#define BITSET_PREFIX_SUM(x, b) \
+   __bitset_prefix_sum(x, b, ARRAY_SIZE(x))
+
 /* Get first bit set in a bitset.
  */
 static inline int