How can I optimize CPU usage about the memcpy operation?
0
I have checked below alternative memcpy_avx is faster than std::memcpy.
But in terms of CPU usage, memcpy_avx is almost same with std::memcpy.
Do you know the good alternative solution to reduce CPU usage when memcpy operation is needed?
#define ALIGN(ptr, align) (((ptr) + (align) - 1) & ~((align) - 1))
void *memcpy_avx(void *dest, const void *src, size_t n)
{
char * d = static_cast<char*>(dest);
const char * s = static_cast<const char*>(src);
/* fall back to memcpy() if misaligned */
if ((reinterpret_cast<uintptr_t>(d) & 31) != (reinterpret_cast<uintptr_t>(s) & 31))
return memcpy(d, s, n);
if (reinterpret_cast<uintptr_t>(d) & 31) {
uintptr_t header_bytes = 32 - (reinterpret_cast<uintptr_t>(d) & 31);
assert(header_bytes < 32);
memcpy(d, s, min(header_bytes, n));
d = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(d), 32));
s = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(s), 32));
n -= min(header_bytes, n);
}
for (; n >= 64; s += 64, d += 64, n -= 64) {
__m256i *dest_cacheline = (__m256i *)d;
__m256i *src_cacheline = (__m256i *)s;
__m256i temp1 = _mm256_stream_load_si256(src_cacheline + 0);
__m256i temp2 = _mm256_stream_load_si256(src_cacheline + 1);
_mm256_stream_si256(dest_cacheline + 0, temp1);
_mm256_stream_si256(dest_cacheline + 1, temp2);
}
if (n > 0)
memcpy(d, s, n);
return dest;
}
optimization cpu-usage memcpy neon
asked Nov 23 '18 at 13:07
HercoaHercoa
1
add a comment |
0
I have checked below alternative memcpy_avx is faster than std::memcpy.
But in terms of CPU usage, memcpy_avx is almost same with std::memcpy.
Do you know the good alternative solution to reduce CPU usage when memcpy operation is needed?
#define ALIGN(ptr, align) (((ptr) + (align) - 1) & ~((align) - 1))
void *memcpy_avx(void *dest, const void *src, size_t n)
{
char * d = static_cast<char*>(dest);
const char * s = static_cast<const char*>(src);
/* fall back to memcpy() if misaligned */
if ((reinterpret_cast<uintptr_t>(d) & 31) != (reinterpret_cast<uintptr_t>(s) & 31))
return memcpy(d, s, n);
if (reinterpret_cast<uintptr_t>(d) & 31) {
uintptr_t header_bytes = 32 - (reinterpret_cast<uintptr_t>(d) & 31);
assert(header_bytes < 32);
memcpy(d, s, min(header_bytes, n));
d = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(d), 32));
s = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(s), 32));
n -= min(header_bytes, n);
}
for (; n >= 64; s += 64, d += 64, n -= 64) {
__m256i *dest_cacheline = (__m256i *)d;
__m256i *src_cacheline = (__m256i *)s;
__m256i temp1 = _mm256_stream_load_si256(src_cacheline + 0);
__m256i temp2 = _mm256_stream_load_si256(src_cacheline + 1);
_mm256_stream_si256(dest_cacheline + 0, temp1);
_mm256_stream_si256(dest_cacheline + 1, temp2);
}
if (n > 0)
memcpy(d, s, n);
return dest;
}
optimization cpu-usage memcpy neon
asked Nov 23 '18 at 13:07
HercoaHercoa
1
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27
add a comment |
0
0
0
I have checked below alternative memcpy_avx is faster than std::memcpy.
But in terms of CPU usage, memcpy_avx is almost same with std::memcpy.
Do you know the good alternative solution to reduce CPU usage when memcpy operation is needed?
#define ALIGN(ptr, align) (((ptr) + (align) - 1) & ~((align) - 1))
void *memcpy_avx(void *dest, const void *src, size_t n)
{
char * d = static_cast<char*>(dest);
const char * s = static_cast<const char*>(src);
/* fall back to memcpy() if misaligned */
if ((reinterpret_cast<uintptr_t>(d) & 31) != (reinterpret_cast<uintptr_t>(s) & 31))
return memcpy(d, s, n);
if (reinterpret_cast<uintptr_t>(d) & 31) {
uintptr_t header_bytes = 32 - (reinterpret_cast<uintptr_t>(d) & 31);
assert(header_bytes < 32);
memcpy(d, s, min(header_bytes, n));
d = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(d), 32));
s = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(s), 32));
n -= min(header_bytes, n);
}
for (; n >= 64; s += 64, d += 64, n -= 64) {
__m256i *dest_cacheline = (__m256i *)d;
__m256i *src_cacheline = (__m256i *)s;
__m256i temp1 = _mm256_stream_load_si256(src_cacheline + 0);
__m256i temp2 = _mm256_stream_load_si256(src_cacheline + 1);
_mm256_stream_si256(dest_cacheline + 0, temp1);
_mm256_stream_si256(dest_cacheline + 1, temp2);
}
if (n > 0)
memcpy(d, s, n);
return dest;
}
optimization cpu-usage memcpy neon
asked Nov 23 '18 at 13:07
HercoaHercoa
1
I have checked below alternative memcpy_avx is faster than std::memcpy.
But in terms of CPU usage, memcpy_avx is almost same with std::memcpy.
Do you know the good alternative solution to reduce CPU usage when memcpy operation is needed?
#define ALIGN(ptr, align) (((ptr) + (align) - 1) & ~((align) - 1))
void *memcpy_avx(void *dest, const void *src, size_t n)
{
char * d = static_cast<char*>(dest);
const char * s = static_cast<const char*>(src);
/* fall back to memcpy() if misaligned */
if ((reinterpret_cast<uintptr_t>(d) & 31) != (reinterpret_cast<uintptr_t>(s) & 31))
return memcpy(d, s, n);
if (reinterpret_cast<uintptr_t>(d) & 31) {
uintptr_t header_bytes = 32 - (reinterpret_cast<uintptr_t>(d) & 31);
assert(header_bytes < 32);
memcpy(d, s, min(header_bytes, n));
d = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(d), 32));
s = reinterpret_cast<char *>(ALIGN(reinterpret_cast<uintptr_t>(s), 32));
n -= min(header_bytes, n);
}
for (; n >= 64; s += 64, d += 64, n -= 64) {
__m256i *dest_cacheline = (__m256i *)d;
__m256i *src_cacheline = (__m256i *)s;
__m256i temp1 = _mm256_stream_load_si256(src_cacheline + 0);
__m256i temp2 = _mm256_stream_load_si256(src_cacheline + 1);
_mm256_stream_si256(dest_cacheline + 0, temp1);
_mm256_stream_si256(dest_cacheline + 1, temp2);
}
if (n > 0)
memcpy(d, s, n);
return dest;
}
optimization cpu-usage memcpy neon
optimization cpu-usage memcpy neon
asked Nov 23 '18 at 13:07
HercoaHercoa
1
asked Nov 23 '18 at 13:07
HercoaHercoa
1
asked Nov 23 '18 at 13:07
HercoaHercoa
1
asked Nov 23 '18 at 13:07
HercoaHercoa
1
asked Nov 23 '18 at 13:07
HercoaHercoa
1
1
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27
add a comment |
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53447303%2fhow-can-i-optimize-cpu-usage-about-the-memcpy-operation%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53447303%2fhow-can-i-optimize-cpu-usage-about-the-memcpy-operation%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Such a transfer operation is essentially memory bound, there is no processing. So nothing you can remove. Maybe you can arrange DMA transfers between main memory and a device such as the graphics card/gpu, and back. This could come virtually for free (for large transfers).
– Yves Daoust
Nov 23 '18 at 13:27