llvm-project/libclc/generic/lib/shared
Aaron Watry f991505d02 vload/vstore: Use casts instead of scalarizing everything in CLC version
This generates bitcode which is indistinguishable from what was
hand-written for int32 types in v[load|store]_impl.ll.

v4: Use vec2+scalar for vec3 load/stores to prevent corruption (per Tom)
v3: Also remove unused generic/lib/shared/v[load|store]_impl.ll
v2: (Per Matt Arsenault) Fix alignment issues with vector load stores

Signed-off-by: Aaron Watry <awatry@gmail.com>
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
CC: Matt Arsenault <Matthew.Arsenault@amd.com>
CC: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 216069
2014-08-20 13:58:57 +00:00
..
clamp.cl Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
clamp.inc Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
max.cl Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
max.inc Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
min.cl Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
min.inc Add __CLC_ prefix to all macro definitions in headers 2013-07-08 17:27:02 +00:00
vload.cl vload/vstore: Use casts instead of scalarizing everything in CLC version 2014-08-20 13:58:57 +00:00
vstore.cl vload/vstore: Use casts instead of scalarizing everything in CLC version 2014-08-20 13:58:57 +00:00