[dpdk-dev] [PATCH v3 1/2] eal: add API to align integer to previous power of 2

[Pavan Nikhilesh]

Add 32b and 64b API's to align the given integer to the previous power
of 2.

Signed-off-by: Pavan Nikhilesh <pbhagavatula at caviumnetworks.com>
---
 v3 Changes:
 - Move commonly used code to rte_combine(32/64)ms1b so that it can be reused.

 v2 Changes:
 - Modified api name to `rte_align(32/64)prevpow2` from
 `rte_align(32/64)lowpow2`.
 - corrected fuction to return if the integer is already aligned to
 power of 2.

 lib/librte_eal/common/include/rte_common.h | 92 ++++++++++++++++++++++++++----
 1 file changed, 81 insertions(+), 11 deletions(-)

diff --git a/lib/librte_eal/common/include/rte_common.h b/lib/librte_eal/common/include/rte_common.h
index c7803e41c..7e147dcf2 100644
--- a/lib/librte_eal/common/include/rte_common.h
+++ b/lib/librte_eal/common/include/rte_common.h
@@ -223,6 +223,51 @@ extern int RTE_BUILD_BUG_ON_detected_error;
 } while(0)
 #endif

+/**
+ * Combines 32b inputs most significant set bits into the least
+ * significant bits to construct a value with the same MSBs as x
+ * but all 1's under it.
+ *
+ * @param x
+ *    The integer whose MSBs need to be combined with its LSBs
+ * @return
+ *    The combined value.
+ */
+static inline uint32_t
+rte_combine32ms1b(register uint32_t x)
+{
+	x |= x >> 1;
+	x |= x >> 2;
+	x |= x >> 4;
+	x |= x >> 8;
+	x |= x >> 16;
+
+	return x;
+}
+
+/**
+ * Combines 64b inputs most significant set bits into the least
+ * significant bits to construct a value with the same MSBs as x
+ * but all 1's under it.
+ *
+ * @param v
+ *    The integer whose MSBs need to be combined with its LSBs
+ * @return
+ *    The combined value.
+ */
+static inline uint64_t
+rte_combine64ms1b(register uint64_t v)
+{
+	v |= v >> 1;
+	v |= v >> 2;
+	v |= v >> 4;
+	v |= v >> 8;
+	v |= v >> 16;
+	v |= v >> 32;
+
+	return v;
+}
+
 /*********** Macros to work with powers of 2 ********/

 /**
@@ -250,15 +295,28 @@ static inline uint32_t
 rte_align32pow2(uint32_t x)
 {
 	x--;
-	x |= x >> 1;
-	x |= x >> 2;
-	x |= x >> 4;
-	x |= x >> 8;
-	x |= x >> 16;
+	x = rte_combine32ms1b(x);

 	return x + 1;
 }

+/**
+ * Aligns input parameter to the previous power of 2
+ *
+ * @param x
+ *   The integer value to algin
+ *
+ * @return
+ *   Input parameter aligned to the previous power of 2
+ */
+static inline uint32_t
+rte_align32prevpow2(uint32_t x)
+{
+	x = rte_combine32ms1b(x);
+
+	return x - (x >> 1);
+}
+
 /**
  * Aligns 64b input parameter to the next power of 2
  *
@@ -272,16 +330,28 @@ static inline uint64_t
 rte_align64pow2(uint64_t v)
 {
 	v--;
-	v |= v >> 1;
-	v |= v >> 2;
-	v |= v >> 4;
-	v |= v >> 8;
-	v |= v >> 16;
-	v |= v >> 32;
+	v = rte_combine64ms1b(v);

 	return v + 1;
 }

+/**
+ * Aligns 64b input parameter to the previous power of 2
+ *
+ * @param v
+ *   The 64b value to align
+ *
+ * @return
+ *   Input parameter aligned to the previous power of 2
+ */
+static inline uint64_t
+rte_align64prevpow2(uint64_t v)
+{
+	v = rte_combine64ms1b(v);
+
+	return v - (v >> 1);
+}
+
 /*********** Macros for calculating min and max **********/

 /**
--
2.16.3