[Mesa-dev] [PATCH 05/12] util: Add power-of-two divisor support to compute_fast_udiv_info

[Jason Ekstrand]

From: Marek Olšák <marek.olsak at amd.com>

---
 src/util/fast_idiv_by_const.c | 21 +++++++++++++++++++++
 src/util/fast_idiv_by_const.h |  5 +++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/src/util/fast_idiv_by_const.c b/src/util/fast_idiv_by_const.c
index 65a9e640789..7b93316268c 100644
--- a/src/util/fast_idiv_by_const.c
+++ b/src/util/fast_idiv_by_const.c
@@ -52,6 +52,27 @@ util_compute_fast_udiv_info(uint64_t D, unsigned num_bits, unsigned UINT_BITS)
    /* The eventual result */
    struct util_fast_udiv_info result;
 
+   if (util_is_power_of_two_or_zero64(D)) {
+      unsigned div_shift = util_logbase2_64(D);
+
+      if (div_shift) {
+         /* Dividing by a power of two. */
+         result.multiplier = 1ull << (UINT_BITS - div_shift);
+         result.pre_shift = 0;
+         result.post_shift = 0;
+         result.increment = 0;
+         return result;
+      } else {
+         /* Dividing by 1. */
+         /* Assuming: floor((num + 1) * (2^32 - 1) / 2^32) = num */
+         result.multiplier = UINT_BITS == 64 ? UINT64_MAX :
+                                               (1ull << UINT_BITS) - 1;
+         result.pre_shift = 0;
+         result.post_shift = 0;
+         result.increment = 1;
+         return result;
+      }
+   }
 
    /* The extra shift implicit in the difference between UINT_BITS and num_bits
     */
diff --git a/src/util/fast_idiv_by_const.h b/src/util/fast_idiv_by_const.h
index 231311f84be..3363fb9ee71 100644
--- a/src/util/fast_idiv_by_const.h
+++ b/src/util/fast_idiv_by_const.h
@@ -98,8 +98,9 @@ util_compute_fast_sdiv_info(int64_t D, unsigned SINT_BITS);
  *   emit("result >>>= UINT_BITS")
  *   if m.post_shift > 0: emit("result >>>= m.post_shift")
  *
- * The shifts by UINT_BITS may be "free" if the high half of the full multiply
- * is put in a separate register.
+ * This second version works even if D is a power of two.  The shifts by
+ * UINT_BITS may be "free" if the high half of the full multiply is put in a
+ * separate register.
  *
  * saturated_increment(n) means "increment n unless it would wrap to 0," i.e.
  *   if n == (1 << UINT_BITS)-1: result = n
-- 
2.19.0