8000 MAINT: restore auto-vectorization of inplace operations by juliantaylor · Pull Request #8852 · numpy/numpy · GitHub
[go: up one dir, main page]
Skip to content

MAINT: restore auto-vectorization of inplace operations #8852

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
merged 1 commit into from
Mar 27, 2017
Merged

MAINT: restore auto-vectorization of inplace operations #8852

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
39 changes: 35 additions & 4 deletions numpy/core/src/umath/loops.c.src
View file
Open in desktop
8C9B
Original file line number Diff line number Diff line change
Expand Up @@ -138,38 +138,69 @@
tout * out = (tout *)op1; \
op; \
}
/*
* unfortunately gcc 6/7 regressed and we need to give it additional hints to
* vectorize inplace operations (PR80198)
* must only be used after op1 == ip1 or ip2 has been checked
* TODO: using ivdep might allow other compilers to vectorize too
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if someone cares about other compilers, you can likely use this type of pragma there too. Last I checked clang could not vectorize this code, with the pragma it might be able to but it needs testing.

*/
#if __GNUC__ >= 6
#define IVDEP_LOOP _Pragma("GCC ivdep")
#else
#define IVDEP_LOOP
#endif
#define BASE_BINARY_LOOP_INP(tin, tout, op) \
char *ip1 = args[0], *ip2 = args[1], *op1 = args[2];\
npy_intp is1 = steps[0], is2 = steps[1], os1 = steps[2];\
npy_intp n = dimensions[0];\
npy_intp i;\
IVDEP_LOOP \
for(i = 0; i < n; i++, ip1 += is1, ip2 += is2, op1 += os1) { \
const tin in1 = *(tin *)ip1; \
const tin in2 = *(tin *)ip2; \
tout * out = (tout *)op1; \
op; \
}
#define BASE_BINARY_LOOP_S(tin, tout, cin, cinp, vin, vinp, op) \
const tin cin = *(tin *)cinp; \
BINARY_LOOP { \
const tin vin = *(tin *)vinp; \
tout * out = (tout *)op1; \
op; \
}
/* PR80198 again, scalar works without the pragma */
#define BASE_BINARY_LOOP_S_INP(tin, tout, cin, cinp, vin, vinp, op) \
const tin cin = *(tin *)cinp; \
BINARY_LOOP { \
const tin vin = *(tin *)vinp; \
tout * out = (tout *)vinp; \
op; \
}
#define BINARY_LOOP_FAST(tin, tout, op) \
do { \
/* condition allows compiler to optimize the generic macro */ \
if (IS_BINARY_CONT(tin, tout)) { \
if (args[2] == args[0]) { \
BASE_BINARY_LOOP(tin, tout, op) \
BASE_BINARY_LOOP_INP(tin, tout, op) \
} \
else if (args[2] == args[1]) { \
BASE_BINARY_LOOP(tin, tout, op) \
BASE_BINARY_LOOP_INP(tin, tout, op) \
} \
else { \
BASE_BINARY_LOOP(tin, tout, op) \
} \
} \
else if (IS_BINARY_CONT_S1(tin, tout)) { \
if (args[1] == args[2]) { \
BASE_BINARY_LOOP_S(tin, tout, in1, args[0], in2, ip2, op) \
BASE_BINARY_LOOP_S_INP(tin, tout, in1, args[0], in2, ip2, op) \
} \
else { \
BASE_BINARY_LOOP_S(tin, tout, in1, args[0], in2, ip2, op) \
} \
} \
else if (IS_BINARY_CONT_S2(tin, tout)) { \
if (args[0] == args[2]) { \
BASE_BINARY_LOOP_S(tin, tout, in2, args[1], in1, ip1, op) \
BASE_BINARY_LOOP_S_INP(tin, tout, in2, args[1], in1, ip1, op) \
} \
else { \
BASE_BINARY_LOOP_S(tin, tout, in2, args[1], in1, ip1, op) \
Expand Down
0