[dpdk-dev] [PATCH v6 2/3] app/test: run-time dispatch over memcpy perf test

[Xiaoyun Li <xiaoyun.li@intel.com>]

This patch modifies assignment of alignment unit from build-time
to run-time based on CPU flags that machine supports.

Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
---
 test/test/test_memcpy_perf.c | 40 +++++++++++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 13 deletions(-)

diff --git a/test/test/test_memcpy_perf.c b/test/test/test_memcpy_perf.c
index ff3aaaa..33def3b 100644
--- a/test/test/test_memcpy_perf.c
+++ b/test/test/test_memcpy_perf.c
@@ -79,13 +79,7 @@ static size_t buf_sizes[TEST_VALUE_RANGE];
 #define TEST_BATCH_SIZE         100
 
 /* Data is aligned on this many bytes (power of 2) */
-#ifdef RTE_MACHINE_CPUFLAG_AVX512F
-#define ALIGNMENT_UNIT          64
-#elif defined RTE_MACHINE_CPUFLAG_AVX2
-#define ALIGNMENT_UNIT          32
-#else /* RTE_MACHINE_CPUFLAG */
-#define ALIGNMENT_UNIT          16
-#endif /* RTE_MACHINE_CPUFLAG */
+static uint8_t alignment_unit = 16;
 
 /*
  * Pointers used in performance tests. The two large buffers are for uncached
@@ -100,20 +94,39 @@ static int
 init_buffers(void)
 {
 	unsigned i;
+#ifdef CC_SUPPORT_AVX512
+	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX512F))
+		alignment_unit = 64;
+	else
+#endif
+#ifdef CC_SUPPORT_AVX2
+	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
+		alignment_unit = 32;
+	else
+#endif
+		alignment_unit = 16;
 
-	large_buf_read = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
+	large_buf_read = rte_malloc("memcpy",
+				    LARGE_BUFFER_SIZE + alignment_unit,
+				    alignment_unit);
 	if (large_buf_read == NULL)
 		goto error_large_buf_read;
 
-	large_buf_write = rte_malloc("memcpy", LARGE_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
+	large_buf_write = rte_malloc("memcpy",
+				     LARGE_BUFFER_SIZE + alignment_unit,
+				     alignment_unit);
 	if (large_buf_write == NULL)
 		goto error_large_buf_write;
 
-	small_buf_read = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
+	small_buf_read = rte_malloc("memcpy",
+				    SMALL_BUFFER_SIZE + alignment_unit,
+				    alignment_unit);
 	if (small_buf_read == NULL)
 		goto error_small_buf_read;
 
-	small_buf_write = rte_malloc("memcpy", SMALL_BUFFER_SIZE + ALIGNMENT_UNIT, ALIGNMENT_UNIT);
+	small_buf_write = rte_malloc("memcpy",
+				     SMALL_BUFFER_SIZE + alignment_unit,
+				     alignment_unit);
 	if (small_buf_write == NULL)
 		goto error_small_buf_write;
 
@@ -153,7 +166,7 @@ static inline size_t
 get_rand_offset(size_t uoffset)
 {
 	return ((rte_rand() % (LARGE_BUFFER_SIZE - SMALL_BUFFER_SIZE)) &
-			~(ALIGNMENT_UNIT - 1)) + uoffset;
+			~(alignment_unit - 1)) + uoffset;
 }
 
 /* Fill in source and destination addresses. */
@@ -321,7 +334,8 @@ perf_test(void)
 		   "(bytes)        (ticks)        (ticks)        (ticks)        (ticks)\n"
 		   "------- -------------- -------------- -------------- --------------");
 
-	printf("\n========================== %2dB aligned ============================", ALIGNMENT_UNIT);
+	printf("\n========================= %2dB aligned ============================",
+		alignment_unit);
 	/* Do aligned tests where size is a variable */
 	perf_test_variable_aligned();
 	printf("\n------- -------------- -------------- -------------- --------------");
-- 
2.7.4