Skip to content

Allow to do gemv and ger buffer allocation on the stack #482

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

Merged
xianyi merged 1 commit into from
Jan 1, 2015
Merged

Allow to do gemv and ger buffer allocation on the stack #482

Show file tree
Hide file tree
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
4 changes: 4 additions & 0 deletions Makefile.system
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,6 +305,10 @@ ifdef SANITY_CHECK
CCOMMON_OPT += -DSANITY_CHECK -DREFNAME=$(*F)f$(BU)
endif

ifdef MAX_STACK_ALLOC
CCOMMON_OPT += -DMAX_STACK_ALLOC=$(MAX_STACK_ALLOC)
endif

#
# Architecture dependent settings
#
Expand Down
16 changes: 15 additions & 1 deletion interface/gemv.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,7 +208,18 @@ void CNAME(enum CBLAS_ORDER order,
if (incx < 0) x -= (lenx - 1) * incx;
if (incy < 0) y -= (leny - 1) * incy;

#ifdef MAX_STACK_ALLOC
int stack_alloc_size = m + n;
if(stack_alloc_size < 128)
//dgemv_n.S require a 128 bytes buffer
stack_alloc_size = 128;
if(stack_alloc_size > MAX_STACK_ALLOC / sizeof(FLOAT))
stack_alloc_size = 0;
FLOAT stack_buffer[stack_alloc_size];
buffer = stack_alloc_size ? stack_buffer : (FLOAT *)blas_memory_alloc(1);
#else
buffer = (FLOAT *)blas_memory_alloc(1);
#endif

#ifdef SMP

Expand Down Expand Up @@ -237,7 +248,10 @@ void CNAME(enum CBLAS_ORDER order,
}
#endif

blas_memory_free(buffer);
#ifdef MAX_STACK_ALLOC
if(!stack_alloc_size)
#endif
blas_memory_free(buffer);

FUNCTION_PROFILE_END(1, m * n + m + n, 2 * m * n);

Expand Down
13 changes: 12 additions & 1 deletion interface/ger.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,15 @@ void CNAME(enum CBLAS_ORDER order,
if (incy < 0) y -= (n - 1) * incy;
if (incx < 0) x -= (m - 1) * incx;

#ifdef MAX_STACK_ALLOC
int stack_alloc_size = m;
if(stack_alloc_size > MAX_STACK_ALLOC / sizeof(FLOAT))
stack_alloc_size = 0;
FLOAT stack_buffer[stack_alloc_size];
buffer = stack_alloc_size ? stack_buffer : (FLOAT *)blas_memory_alloc(1);
#else
buffer = (FLOAT *)blas_memory_alloc(1);
#endif

#ifdef SMPTEST
nthreads = num_cpu_avail(2);
Expand All @@ -190,7 +198,10 @@ void CNAME(enum CBLAS_ORDER order,
}
#endif

blas_memory_free(buffer);
#ifdef MAX_STACK_ALLOC
if(!stack_alloc_size)
#endif
blas_memory_free(buffer);

FUNCTION_PROFILE_END(1, m * n + m + n, 2 * m * n);

Expand Down
2 changes: 1 addition & 1 deletion kernel/x86_64/sgemv_t_4.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -302,7 +302,7 @@ int CNAME(BLASLONG m, BLASLONG n, BLASLONG dummy1, FLOAT alpha, FLOAT *a, BLASLO
if ( n < 1 ) return(0);

xbuffer = buffer;
ytemp = buffer + NBMAX;
ytemp = buffer + (m < NBMAX ? m : NBMAX);

n0 = n / NBMAX;
n1 = (n % NBMAX) >> 2 ;
Expand Down