[dpdk-dev] [PATCH v4] 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. Update common auto test to include test for previous power of 2 for
both 32 and 64bit integers.

Signed-off-by: Pavan Nikhilesh <pbhagavatula at caviumnetworks.com>
---
 v4 Changes:
 - Squash patchset into a single patch.
 - Use %PRIu64 instead of %lu

 lib/librte_eal/common/include/rte_common.h | 92 ++++++++++++++++++++++++++----
 test/test/test_common.c                    | 26 +++++++++
 2 files changed, 107 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 **********/

 /**
diff --git a/test/test/test_common.c b/test/test/test_common.c
index d0342430f..7361693b8 100644
--- a/test/test/test_common.c
+++ b/test/test/test_common.c
@@ -3,6 +3,7 @@
  */

 #include <stdio.h>
+#include <inttypes.h>
 #include <string.h>
 #include <math.h>
 #include <rte_common.h>
@@ -70,6 +71,9 @@ test_align(void)
 #define FAIL_ALIGN(x, i, p)\
 	{printf(x "() test failed: %u %u\n", i, p);\
 	return -1;}
+#define FAIL_ALIGN64(x, j, q)\
+	{printf(x "() test failed: %"PRIu64" %"PRIu64"\n", j, q);\
+	return -1; }
 #define ERROR_FLOOR(res, i, pow) \
 		(res % pow) || 						/* check if not aligned */ \
 		((res / pow) != (i / pow))  		/* check if correct alignment */
@@ -80,6 +84,7 @@ test_align(void)
 			val / pow != (i / pow) + 1)		/* if not aligned, hence +1 */

 	uint32_t i, p, val;
+	uint64_t j, q;

 	for (i = 1, p = 1; i <= MAX_NUM; i ++) {
 		if (rte_align32pow2(i) != p)
@@ -88,6 +93,27 @@ test_align(void)
 			p <<= 1;
 	}

+	for (i = 1, p = 1; i <= MAX_NUM; i++) {
+		if (rte_align32prevpow2(i) != p)
+			FAIL_ALIGN("rte_align32prevpow2", i, p);
+		if (rte_is_power_of_2(i + 1))
+			p = i + 1;
+	}
+
+	for (j = 1, q = 1; j <= MAX_NUM ; j++) {
+		if (rte_align64pow2(j) != q)
+			FAIL_ALIGN64("rte_align64pow2", j, q);
+		if (j == q)
+			q <<= 1;
+	}
+
+	for (j = 1, q = 1; j <= MAX_NUM ; j++) {
+		if (rte_align64prevpow2(j) != q)
+			FAIL_ALIGN64("rte_align64prevpow2", j, q);
+		if (rte_is_power_of_2(j + 1))
+			q = j + 1;
+	}
+
 	for (p = 2; p <= MAX_NUM; p <<= 1) {

 		if (!rte_is_power_of_2(p))
--
2.16.3