Skip to content

Fix mathops.h to build with cuda 12. #31

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
okanaganrusty wants to merge 1 commit into
base: livepeer
Choose a base branch
from
+23 −3
Open

Fix mathops.h to build with cuda 12. #31

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 23 additions & 3 deletions libavcodec/x86/mathops.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,12 +35,20 @@
static av_always_inline av_const int MULL(int a, int b, unsigned shift)
{
int rt, dummy;
if (__builtin_constant_p(shift))
__asm__ (
"imull %3 \n\t"
"shrdl %4, %%edx, %%eax \n\t"
:"=a"(rt), "=d"(dummy)
:"a"(a), "rm"(b), "ci"((uint8_t)shift)
:"a"(a), "rm"(b), "i"(shift & 0x1F)
);
else
__asm__ (
"imull %3 \n\t"
"shrdl %4, %%edx, %%eax \n\t"
:"=a"(rt), "=d"(dummy)
:"a"(a), "rm"(b), "c"((uint8_t)shift)
);
return rt;
}

Expand Down Expand Up @@ -113,19 +121,31 @@ __asm__ volatile(\
// avoid +32 for shift optimization (gcc should do that ...)
#define NEG_SSR32 NEG_SSR32
static inline int32_t NEG_SSR32( int32_t a, int8_t s){
if (__builtin_constant_p(s))
__asm__ ("sarl %1, %0\n\t"
: "+r" (a)
: "ic" ((uint8_t)(-s))
: "i" (-s & 0x1F)
);
else
__asm__ ("sarl %1, %0\n\t"
: "+r" (a)
: "c" ((uint8_t)(-s))
);
return a;
}

#define NEG_USR32 NEG_USR32
static inline uint32_t NEG_USR32(uint32_t a, int8_t s){
if (__builtin_constant_p(s))
__asm__ ("shrl %1, %0\n\t"
: "+r" (a)
: "ic" ((uint8_t)(-s))
: "i" (-s & 0x1F)
);
else
__asm__ ("shrl %1, %0\n\t"
: "+r" (a)
: "c" ((uint8_t)(-s))
);
return a;
}

Expand Down