* [Qemu-devel] [PATCH v2] vectorize is_dup_page
@ 2011-12-23 15:17 Paolo Bonzini
2012-01-13 15:55 ` Paolo Bonzini
2012-01-13 16:54 ` Anthony Liguori
0 siblings, 2 replies; 3+ messages in thread
From: Paolo Bonzini @ 2011-12-23 15:17 UTC (permalink / raw)
To: qemu-devel
is_dup_page is already proceeding in 32-bit chunks. Changing it
to 16 bytes using Altivec or SSE is easy.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch_init.c | 28 ++++++++++++++++++++++------
1 files changed, 22 insertions(+), 6 deletions(-)
diff --git a/arch_init.c b/arch_init.c
index d4c92b0..8466ffb 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -94,14 +94,30 @@ const uint32_t arch_type = QEMU_ARCH;
#define RAM_SAVE_FLAG_EOS 0x10
#define RAM_SAVE_FLAG_CONTINUE 0x20
-static int is_dup_page(uint8_t *page, uint8_t ch)
+#ifdef __ALTIVEC__
+#include <altivec.h>
+#define VECTYPE vector unsigned char
+#define SPLAT(p) vec_splat(vec_ld(0, p), 0)
+#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
+#elif defined __SSE2__
+#include <emmintrin.h>
+#define VECTYPE __m128i
+#define SPLAT(p) _mm_set1_epi8(*(p))
+#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
+#else
+#define VECTYPE unsigned long
+#define SPLAT(p) (*(p) * (~0UL / 255))
+#define ALL_EQ(v1, v2) ((v1) == (v2))
+#endif
+
+static int is_dup_page(uint8_t *page)
{
- uint32_t val = ch << 24 | ch << 16 | ch << 8 | ch;
- uint32_t *array = (uint32_t *)page;
+ VECTYPE *p = (VECTYPE *)page;
+ VECTYPE val = SPLAT(page);
int i;
- for (i = 0; i < (TARGET_PAGE_SIZE / 4); i++) {
- if (array[i] != val) {
+ for (i = 0; i < TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
+ if (!ALL_EQ(val, p[i])) {
return 0;
}
}
@@ -135,7 +151,7 @@ static int ram_save_block(QEMUFile *f)
p = block->host + offset;
- if (is_dup_page(p, *p)) {
+ if (is_dup_page(p)) {
qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
if (!cont) {
qemu_put_byte(f, strlen(block->idstr));
--
1.7.7.1
^ permalink raw reply related [flat|nested] 3+ messages in thread* Re: [Qemu-devel] [PATCH v2] vectorize is_dup_page
2011-12-23 15:17 [Qemu-devel] [PATCH v2] vectorize is_dup_page Paolo Bonzini
@ 2012-01-13 15:55 ` Paolo Bonzini
2012-01-13 16:54 ` Anthony Liguori
1 sibling, 0 replies; 3+ messages in thread
From: Paolo Bonzini @ 2012-01-13 15:55 UTC (permalink / raw)
To: qemu-devel
On 12/23/2011 04:17 PM, Paolo Bonzini wrote:
> is_dup_page is already proceeding in 32-bit chunks. Changing it
> to 16 bytes using Altivec or SSE is easy.
>
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
> ---
> arch_init.c | 28 ++++++++++++++++++++++------
> 1 files changed, 22 insertions(+), 6 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index d4c92b0..8466ffb 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -94,14 +94,30 @@ const uint32_t arch_type = QEMU_ARCH;
> #define RAM_SAVE_FLAG_EOS 0x10
> #define RAM_SAVE_FLAG_CONTINUE 0x20
>
> -static int is_dup_page(uint8_t *page, uint8_t ch)
> +#ifdef __ALTIVEC__
> +#include<altivec.h>
> +#define VECTYPE vector unsigned char
> +#define SPLAT(p) vec_splat(vec_ld(0, p), 0)
> +#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
> +#elif defined __SSE2__
> +#include<emmintrin.h>
> +#define VECTYPE __m128i
> +#define SPLAT(p) _mm_set1_epi8(*(p))
> +#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
> +#else
> +#define VECTYPE unsigned long
> +#define SPLAT(p) (*(p) * (~0UL / 255))
> +#define ALL_EQ(v1, v2) ((v1) == (v2))
> +#endif
> +
> +static int is_dup_page(uint8_t *page)
> {
> - uint32_t val = ch<< 24 | ch<< 16 | ch<< 8 | ch;
> - uint32_t *array = (uint32_t *)page;
> + VECTYPE *p = (VECTYPE *)page;
> + VECTYPE val = SPLAT(page);
> int i;
>
> - for (i = 0; i< (TARGET_PAGE_SIZE / 4); i++) {
> - if (array[i] != val) {
> + for (i = 0; i< TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
> + if (!ALL_EQ(val, p[i])) {
> return 0;
> }
> }
> @@ -135,7 +151,7 @@ static int ram_save_block(QEMUFile *f)
>
> p = block->host + offset;
>
> - if (is_dup_page(p, *p)) {
> + if (is_dup_page(p)) {
> qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
> if (!cont) {
> qemu_put_byte(f, strlen(block->idstr));
Ping.
Paolo
^ permalink raw reply [flat|nested] 3+ messages in thread* Re: [Qemu-devel] [PATCH v2] vectorize is_dup_page
2011-12-23 15:17 [Qemu-devel] [PATCH v2] vectorize is_dup_page Paolo Bonzini
2012-01-13 15:55 ` Paolo Bonzini
@ 2012-01-13 16:54 ` Anthony Liguori
1 sibling, 0 replies; 3+ messages in thread
From: Anthony Liguori @ 2012-01-13 16:54 UTC (permalink / raw)
To: Paolo Bonzini; +Cc: qemu-devel
On 12/23/2011 09:17 AM, Paolo Bonzini wrote:
> is_dup_page is already proceeding in 32-bit chunks. Changing it
> to 16 bytes using Altivec or SSE is easy.
>
> Signed-off-by: Paolo Bonzini<pbonzini@redhat.com>
Applied. Thanks.
Regards,
Anthony Liguori
> ---
> arch_init.c | 28 ++++++++++++++++++++++------
> 1 files changed, 22 insertions(+), 6 deletions(-)
>
> diff --git a/arch_init.c b/arch_init.c
> index d4c92b0..8466ffb 100644
> --- a/arch_init.c
> +++ b/arch_init.c
> @@ -94,14 +94,30 @@ const uint32_t arch_type = QEMU_ARCH;
> #define RAM_SAVE_FLAG_EOS 0x10
> #define RAM_SAVE_FLAG_CONTINUE 0x20
>
> -static int is_dup_page(uint8_t *page, uint8_t ch)
> +#ifdef __ALTIVEC__
> +#include<altivec.h>
> +#define VECTYPE vector unsigned char
> +#define SPLAT(p) vec_splat(vec_ld(0, p), 0)
> +#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
> +#elif defined __SSE2__
> +#include<emmintrin.h>
> +#define VECTYPE __m128i
> +#define SPLAT(p) _mm_set1_epi8(*(p))
> +#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
> +#else
> +#define VECTYPE unsigned long
> +#define SPLAT(p) (*(p) * (~0UL / 255))
> +#define ALL_EQ(v1, v2) ((v1) == (v2))
> +#endif
> +
> +static int is_dup_page(uint8_t *page)
> {
> - uint32_t val = ch<< 24 | ch<< 16 | ch<< 8 | ch;
> - uint32_t *array = (uint32_t *)page;
> + VECTYPE *p = (VECTYPE *)page;
> + VECTYPE val = SPLAT(page);
> int i;
>
> - for (i = 0; i< (TARGET_PAGE_SIZE / 4); i++) {
> - if (array[i] != val) {
> + for (i = 0; i< TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
> + if (!ALL_EQ(val, p[i])) {
> return 0;
> }
> }
> @@ -135,7 +151,7 @@ static int ram_save_block(QEMUFile *f)
>
> p = block->host + offset;
>
> - if (is_dup_page(p, *p)) {
> + if (is_dup_page(p)) {
> qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
> if (!cont) {
> qemu_put_byte(f, strlen(block->idstr));
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2012-01-13 16:54 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-12-23 15:17 [Qemu-devel] [PATCH v2] vectorize is_dup_page Paolo Bonzini
2012-01-13 15:55 ` Paolo Bonzini
2012-01-13 16:54 ` Anthony Liguori
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).