[PATCH] D73237: [CUDA] Fix order of memcpy arguments in __shfl_*(<64-bit type>).

[Artem Belevich via Phabricator via cfe-commits]

tra created this revision.
tra added a reviewer: jlebar.
Herald added subscribers: sanjoy.google, bixia.
Herald added a project: clang.

Wrong argument order resulted in broken shfl ops for 64-bit types.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D73237

Files:
  clang/lib/Headers/__clang_cuda_intrinsics.h


Index: clang/lib/Headers/__clang_cuda_intrinsics.h
===================================================================
--- clang/lib/Headers/__clang_cuda_intrinsics.h
+++ clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -45,7 +45,7 @@
     _Static_assert(sizeof(__val) == sizeof(__Bits));                           
\
     _Static_assert(sizeof(__Bits) == 2 * sizeof(int));                         
\
     __Bits __tmp;                                                              
\
-    memcpy(&__val, &__tmp, sizeof(__val));                                     
\
+    memcpy(&__tmp, &__val, sizeof(__val));                                \
     __tmp.__a = ::__FnName(__tmp.__a, __offset, __width);                      
\
     __tmp.__b = ::__FnName(__tmp.__b, __offset, __width);                      
\
     long long __ret;                                                           
\
@@ -129,7 +129,7 @@
     _Static_assert(sizeof(__val) == sizeof(__Bits));                           
\
     _Static_assert(sizeof(__Bits) == 2 * sizeof(int));                         
\
     __Bits __tmp;                                                              
\
-    memcpy(&__val, &__tmp, sizeof(__val));                                     
\
+    memcpy(&__tmp, &__val, sizeof(__val));                                     
\
     __tmp.__a = ::__FnName(__mask, __tmp.__a, __offset, __width);              
\
     __tmp.__b = ::__FnName(__mask, __tmp.__b, __offset, __width);              
\
     long long __ret;                                                           
\



Index: clang/lib/Headers/__clang_cuda_intrinsics.h
===================================================================
--- clang/lib/Headers/__clang_cuda_intrinsics.h
+++ clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -45,7 +45,7 @@
     _Static_assert(sizeof(__val) == sizeof(__Bits));                           \
     _Static_assert(sizeof(__Bits) == 2 * sizeof(int));                         \
     __Bits __tmp;                                                              \
-    memcpy(&__val, &__tmp, sizeof(__val));                                     \
+    memcpy(&__tmp, &__val, sizeof(__val));                                \
     __tmp.__a = ::__FnName(__tmp.__a, __offset, __width);                      \
     __tmp.__b = ::__FnName(__tmp.__b, __offset, __width);                      \
     long long __ret;                                                           \
@@ -129,7 +129,7 @@
     _Static_assert(sizeof(__val) == sizeof(__Bits));                           \
     _Static_assert(sizeof(__Bits) == 2 * sizeof(int));                         \
     __Bits __tmp;                                                              \
-    memcpy(&__val, &__tmp, sizeof(__val));                                     \
+    memcpy(&__tmp, &__val, sizeof(__val));                                     \
     __tmp.__a = ::__FnName(__mask, __tmp.__a, __offset, __width);              \
     __tmp.__b = ::__FnName(__mask, __tmp.__b, __offset, __width);              \
     long long __ret;                                                           \

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits