From: Tyler Retzlaff <roretzla@linux.microsoft.com>
To: dev@dpdk.org
Cc: Bruce Richardson <bruce.richardson@intel.com>,
Cristian Dumitrescu <cristian.dumitrescu@intel.com>,
David Hunt <david.hunt@intel.com>,
Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>,
Ruifeng Wang <ruifeng.wang@arm.com>,
Sameh Gobriel <sameh.gobriel@intel.com>,
Tyler Retzlaff <roretzla@linux.microsoft.com>,
Vladimir Medvedkin <vladimir.medvedkin@intel.com>,
Yipeng Wang <yipeng1.wang@intel.com>
Subject: [PATCH 4/5] member: use abstracted bit count functions
Date: Wed, 1 Nov 2023 18:05:31 -0700 [thread overview]
Message-ID: <1698887132-5347-5-git-send-email-roretzla@linux.microsoft.com> (raw)
In-Reply-To: <1698887132-5347-1-git-send-email-roretzla@linux.microsoft.com>
Use rte_ctz64 instead of __builtin_ctzl
Fixes: 18898c4d06f9 ("eal: use abstracted bit count functions")
Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
lib/member/rte_member_vbf.c | 12 ++++++------
lib/member/rte_member_x86.h | 6 +++---
2 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/lib/member/rte_member_vbf.c b/lib/member/rte_member_vbf.c
index 9df4620..6440e35 100644
--- a/lib/member/rte_member_vbf.c
+++ b/lib/member/rte_member_vbf.c
@@ -108,8 +108,8 @@
* div_shift is used for division shift, to be divided by number of bits
* represented by a uint32_t variable
*/
- ss->mul_shift = __builtin_ctzl(ss->num_set);
- ss->div_shift = __builtin_ctzl(32 >> ss->mul_shift);
+ ss->mul_shift = rte_ctz64(ss->num_set);
+ ss->div_shift = rte_ctz64(32 >> ss->mul_shift);
RTE_MEMBER_LOG(DEBUG, "vector bloom filter created, "
"each bloom filter expects %u keys, needs %u bits, %u hashes, "
@@ -174,7 +174,7 @@
}
if (mask) {
- *set_id = __builtin_ctzl(mask) + 1;
+ *set_id = rte_ctz64(mask) + 1;
return 1;
}
@@ -207,7 +207,7 @@
}
for (i = 0; i < num_keys; i++) {
if (mask[i]) {
- set_ids[i] = __builtin_ctzl(mask[i]) + 1;
+ set_ids[i] = rte_ctz64(mask[i]) + 1;
num_matches++;
} else
set_ids[i] = RTE_MEMBER_NO_MATCH;
@@ -233,7 +233,7 @@
mask &= test_bit(bit_loc, ss);
}
while (mask) {
- uint32_t loc = __builtin_ctzl(mask);
+ uint32_t loc = rte_ctz64(mask);
set_id[num_matches] = loc + 1;
num_matches++;
if (num_matches >= match_per_key)
@@ -272,7 +272,7 @@
for (i = 0; i < num_keys; i++) {
match_cnt_t = 0;
while (mask[i]) {
- uint32_t loc = __builtin_ctzl(mask[i]);
+ uint32_t loc = rte_ctz64(mask[i]);
set_ids[i * match_per_key + match_cnt_t] = loc + 1;
match_cnt_t++;
if (match_cnt_t >= match_per_key)
diff --git a/lib/member/rte_member_x86.h b/lib/member/rte_member_x86.h
index 74c8e38..ee830f5 100644
--- a/lib/member/rte_member_x86.h
+++ b/lib/member/rte_member_x86.h
@@ -22,7 +22,7 @@
_mm256_load_si256((__m256i const *)buckets[bucket_id].sigs),
_mm256_set1_epi16(tmp_sig)));
if (hitmask) {
- uint32_t hit_idx = __builtin_ctzl(hitmask) >> 1;
+ uint32_t hit_idx = rte_ctz64(hitmask) >> 1;
buckets[bucket_id].sets[hit_idx] = set_id;
return 1;
}
@@ -38,7 +38,7 @@
_mm256_load_si256((__m256i const *)buckets[bucket_id].sigs),
_mm256_set1_epi16(tmp_sig)));
while (hitmask) {
- uint32_t hit_idx = __builtin_ctzl(hitmask) >> 1;
+ uint32_t hit_idx = rte_ctz64(hitmask) >> 1;
if (buckets[bucket_id].sets[hit_idx] != RTE_MEMBER_NO_MATCH) {
*set_id = buckets[bucket_id].sets[hit_idx];
return 1;
@@ -59,7 +59,7 @@
_mm256_load_si256((__m256i const *)buckets[bucket_id].sigs),
_mm256_set1_epi16(tmp_sig)));
while (hitmask) {
- uint32_t hit_idx = __builtin_ctzl(hitmask) >> 1;
+ uint32_t hit_idx = rte_ctz64(hitmask) >> 1;
if (buckets[bucket_id].sets[hit_idx] != RTE_MEMBER_NO_MATCH) {
set_id[*counter] = buckets[bucket_id].sets[hit_idx];
(*counter)++;
--
1.8.3.1
next prev parent reply other threads:[~2023-11-02 1:06 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-02 1:05 [PATCH 0/5] " Tyler Retzlaff
2023-11-02 1:05 ` [PATCH 1/5] table: " Tyler Retzlaff
2023-11-02 1:05 ` [PATCH 2/5] distributor: " Tyler Retzlaff
2023-11-02 1:05 ` [PATCH 3/5] hash: " Tyler Retzlaff
2023-11-02 1:05 ` Tyler Retzlaff [this message]
2023-11-02 1:05 ` [PATCH 5/5] rcu: " Tyler Retzlaff
2023-11-02 7:39 ` [PATCH 0/5] " Morten Brørup
2023-11-02 15:27 ` Tyler Retzlaff
2023-11-02 15:33 ` Morten Brørup
2023-11-02 15:36 ` Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 " Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 1/5] distributor: " Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 2/5] hash: " Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 3/5] member: " Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 4/5] rcu: " Tyler Retzlaff
2023-11-07 19:10 ` [PATCH v2 5/5] table: " Tyler Retzlaff
2023-11-08 8:25 ` [PATCH v2 0/5] " Morten Brørup
2023-11-07 23:38 ` [PATCH v3 0/7] " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 1/7] distributor: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 2/7] hash: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 3/7] member: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 4/7] rcu: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 5/7] table: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 6/7] distributor: " Tyler Retzlaff
2023-11-07 23:38 ` [PATCH v3 7/7] hash: " Tyler Retzlaff
2023-11-08 8:47 ` CI test system not catching truncation bugs for 32-bit architectures? Morten Brørup
2023-11-08 8:34 ` [PATCH v3 0/7] use abstracted bit count functions Morten Brørup
2023-11-08 16:57 ` Thomas Monjalon
2023-11-08 18:42 ` Tyler Retzlaff
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1698887132-5347-5-git-send-email-roretzla@linux.microsoft.com \
--to=roretzla@linux.microsoft.com \
--cc=bruce.richardson@intel.com \
--cc=cristian.dumitrescu@intel.com \
--cc=david.hunt@intel.com \
--cc=dev@dpdk.org \
--cc=honnappa.nagarahalli@arm.com \
--cc=ruifeng.wang@arm.com \
--cc=sameh.gobriel@intel.com \
--cc=vladimir.medvedkin@intel.com \
--cc=yipeng1.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).