From: Frédéric Recoules <frederic.recoules@xxxxxxxxx>
Note: newer versions of GCC accept that ebx is declared
in the clobber list.
Signed-off-by: Frédéric Recoules <frederic.recoules@xxxxxxxxx>
---
src/pcm/pcm_dmix_i386.h | 93 ++++++++++++++++++++++++++++++---------
src/pcm/pcm_dmix_x86_64.h | 59 ++++++++++++++++++++-----
2 files changed, 120 insertions(+), 32 deletions(-)
diff --git a/src/pcm/pcm_dmix_i386.h b/src/pcm/pcm_dmix_i386.h
index d9bf8f50..b28ae787 100644
--- a/src/pcm/pcm_dmix_i386.h
+++ b/src/pcm/pcm_dmix_i386.h
@@ -26,6 +26,10 @@
*
*/
+#if defined(__GNUC__) && __GNUC__ < 5 && defined(__PIC__)
+# define BOUNDED_EBX
+#endif
+
/*
* for plain i386
*/
@@ -34,8 +38,9 @@ static void MIX_AREAS_16(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_EBX
unsigned int old_ebx;
-
+# endif
/*
* ESI - src
* EDI - dst
@@ -46,8 +51,9 @@ static void MIX_AREAS_16(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_EBX
"\tmovl %%ebx, %[old_ebx]\n" /* ebx is GOT pointer (-fPIC) */
+# endif
/*
* initialization, load ESI, EDI, EBX registers
*/
@@ -140,13 +146,20 @@ static void MIX_AREAS_16(unsigned int size,
"\tjnz 1b\n"
"7:"
+# ifdef BOUNDED_EBX
"\tmovl %[old_ebx], %%ebx\n" /* ebx is GOT pointer (-fPIC) */
-
- : [size] "+m" (size), [old_ebx] "=m" (old_ebx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_EBX
+ , [old_ebx] "=m" (old_ebx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "esi", "edi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_EBX
+ , "ebx"
+# endif
);
}
@@ -158,8 +171,9 @@ static void MIX_AREAS_16_MMX(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_EBX
unsigned int old_ebx;
-
+# endif
/*
* ESI - src
* EDI - dst
@@ -170,8 +184,9 @@ static void MIX_AREAS_16_MMX(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_EBX
"\tmovl %%ebx, %[old_ebx]\n" /* ebx is GOT pointer (-fPIC) */
+# endif
/*
* initialization, load ESI, EDI, EBX registers and clear MM1
*/
@@ -231,13 +246,20 @@ static void MIX_AREAS_16_MMX(unsigned int size,
"\tjnz 1b\n"
"\temms\n"
"5:"
+# ifdef BOUNDED_EBX
"\tmovl %[old_ebx], %%ebx\n" /* ebx is GOT pointer (-fPIC) */
-
- : [size] "+m" (size), [old_ebx] "=m" (old_ebx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_EBX
+ , [old_ebx] "=m" (old_ebx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "esi", "edi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_EBX
+ , "ebx"
+# endif
# ifdef HAVE_MMX
, "mm0", "mm1"
# else
@@ -255,8 +277,9 @@ static void MIX_AREAS_32(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_EBX
unsigned int old_ebx;
-
+# endif
/*
* ESI - src
* EDI - dst
@@ -267,8 +290,9 @@ static void MIX_AREAS_32(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_EBX
"\tmovl %%ebx, %[old_ebx]\n" /* ebx is GOT pointer (-fPIC) */
+# endif
/*
* initialization, load ESI, EDI, EBX registers
*/
@@ -350,13 +374,20 @@ static void MIX_AREAS_32(unsigned int size,
"\tjmp 1b\n"
"6:"
+# ifdef BOUNDED_EBX
"\tmovl %[old_ebx], %%ebx\n" /* ebx is GOT pointer (-fPIC) */
-
- : [size] "+m" (size), [old_ebx] "=m" (old_ebx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_EBX
+ , [old_ebx] "=m" (old_ebx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "esi", "edi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_EBX
+ , "ebx"
+# endif
);
}
@@ -368,8 +399,9 @@ static void MIX_AREAS_24(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_EBX
unsigned int old_ebx;
-
+# endif
/*
* ESI - src
* EDI - dst
@@ -380,8 +412,9 @@ static void MIX_AREAS_24(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_EBX
"\tmovl %%ebx, %[old_ebx]\n" /* ebx is GOT pointer (-fPIC) */
+# endif
/*
* initialization, load ESI, EDI, EBX registers
*/
@@ -456,13 +489,20 @@ static void MIX_AREAS_24(unsigned int size,
"\tjmp 1b\n"
"6:"
+# ifdef BOUNDED_EBX
"\tmovl %[old_ebx], %%ebx\n" /* ebx is GOT pointer (-fPIC) */
-
- : [size] "+m" (size), [old_ebx] "=m" (old_ebx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_EBX
+ , [old_ebx] "=m" (old_ebx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "esi", "edi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_EBX
+ , "ebx"
+# endif
);
}
@@ -474,8 +514,9 @@ static void MIX_AREAS_24_CMOV(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_EBX
unsigned int old_ebx;
-
+# endif
/*
* ESI - src
* EDI - dst
@@ -486,8 +527,9 @@ static void MIX_AREAS_24_CMOV(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_EBX
"\tmovl %%ebx, %[old_ebx]\n" /* ebx is GOT pointer (-fPIC) */
+# endif
/*
* initialization, load ESI, EDI, EBX registers
*/
@@ -555,12 +597,23 @@ static void MIX_AREAS_24_CMOV(unsigned int size,
"\tjnz 1b\n"
"6:"
+# ifdef BOUNDED_EBX
"\tmovl %[old_ebx], %%ebx\n" /* ebx is GOT pointer (-fPIC) */
-
- : [size] "+m" (size), [old_ebx] "=m" (old_ebx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_EBX
+ , [old_ebx] "=m" (old_ebx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "esi", "edi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_EBX
+ , "ebx"
+# endif
);
}
+
+#ifdef BOUNDED_EBX
+# undef BOUNDED_EBX
+#endif
diff --git a/src/pcm/pcm_dmix_x86_64.h b/src/pcm/pcm_dmix_x86_64.h
index 8ad1b2a0..f543a134 100644
--- a/src/pcm/pcm_dmix_x86_64.h
+++ b/src/pcm/pcm_dmix_x86_64.h
@@ -27,6 +27,10 @@
*
*/
+#if defined(__GNUC__) && __GNUC__ < 5 && defined(__PIC__)
+# define BOUNDED_RBX
+#endif
+
/*
* MMX optimized
*/
@@ -35,8 +39,9 @@ static void MIX_AREAS_16(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_RBX
unsigned long long old_rbx;
-
+# endif
/*
* RSI - src
* RDI - dst
@@ -47,8 +52,9 @@ static void MIX_AREAS_16(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_RBX
"\tmovq %%rbx, %[old_rbx]\n"
+# endif
/*
* initialization, load RSI, RDI, RBX registers and clear MM1
*/
@@ -113,13 +119,20 @@ static void MIX_AREAS_16(unsigned int size,
"6:"
"\temms\n"
+# ifdef BOUNDED_RBX
"\tmovq %[old_rbx], %%rbx\n"
-
- : [size] "+m" (size), [old_rbx] "=m" (old_rbx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_RBX
+ , [old_rbx] "=m" (old_rbx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "rsi", "rdi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_RBX
+ , "rbx"
+# endif
# ifdef HAVE_MMX
, "mm0", "mm1"
# else
@@ -137,8 +150,9 @@ static void MIX_AREAS_32(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_RBX
unsigned long long old_rbx;
-
+# endif
/*
* RSI - src
* RDI - dst
@@ -149,8 +163,9 @@ static void MIX_AREAS_32(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_RBX
"\tmovq %%rbx, %[old_rbx]\n"
+# endif
/*
* initialization, load RSI, RDI, RBX registers
*/
@@ -234,13 +249,20 @@ static void MIX_AREAS_32(unsigned int size,
"\tjnz 1b\n"
"6:"
+# ifdef BOUNDED_RBX
"\tmovq %[old_rbx], %%rbx\n"
-
- : [size] "+m" (size), [old_rbx] "=m" (old_rbx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_RBX
+ , [old_rbx] "=m" (old_rbx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "rsi", "rdi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_RBX
+ , "rbx"
+# endif
);
}
@@ -252,8 +274,9 @@ static void MIX_AREAS_24(unsigned int size,
volatile signed int *sum, size_t dst_step,
size_t src_step, size_t sum_step)
{
+# ifdef BOUNDED_RBX
unsigned long long old_rbx;
-
+# endif
/*
* RSI - src
* RDI - dst
@@ -264,8 +287,9 @@ static void MIX_AREAS_24(unsigned int size,
*/
__asm__ __volatile__ (
"\n"
-
+# ifdef BOUNDED_RBX
"\tmovq %%rbx, %[old_rbx]\n"
+# endif
/*
* initialization, load RSI, RDI, RBX registers
*/
@@ -337,12 +361,23 @@ static void MIX_AREAS_24(unsigned int size,
"\tjnz 1b\n"
"6:"
+# ifdef BOUNDED_RBX
"\tmovq %[old_rbx], %%rbx\n"
-
- : [size] "+m" (size), [old_rbx] "=m" (old_rbx)
+# endif
+ : [size] "+m" (size)
+# ifdef BOUNDED_RBX
+ , [old_rbx] "=m" (old_rbx)
+# endif
: [dst] "m" (dst), [src] "m" (src), [sum] "m" (sum),
[dst_step] "m" (dst_step), [src_step] "m" (src_step),
[sum_step] "m" (sum_step)
: "rsi", "rdi", "edx", "ecx", "eax", "memory", "cc"
+# ifndef BOUNDED_RBX
+ , "rbx"
+# endif
);
}
+
+#ifdef BOUNDED_RBX
+# undef BOUNDED_RBX
+#endif
--
2.17.1
Note: it has not been tested but I can not figure out it could break
something because the compiler is now aware that ebx is clobbered.
Curiously, it seems it significantly reduces the size of the code.
