ReinUsesLisp 4e35177e23 shader_ir: Implement VOTE ... Implement VOTE using Nvidia's intrinsics. Documentation about these can be found here https://developer.nvidia.com/reading-between-threads-shader-intrinsics Instead of using portable ARB instructions I opted to use Nvidia intrinsics because these are the closest we have to how Tegra X1 hardware renders. To stub VOTE on non-Nvidia drivers (including nouveau) this commit simulates a GPU with a warp size of one, returning what is meaningful for the instruction being emulated: * anyThreadNV(value) -> value * allThreadsNV(value) -> value * allThreadsEqualNV(value) -> true ballotARB, also known as "uint64_t(activeThreadsNV())", emits VOTE.ANY Rd, PT, PT; on nouveau's compiler. This doesn't match exactly to Nvidia's code VOTE.ALL Rd, PT, PT; Which is emulated with activeThreadsNV() by this commit. In theory this shouldn't really matter since .ANY, .ALL and .EQ affect the predicates (set to PT on those cases) and not the registers.		2019-08-21 14:50:38 -03:00
..
logging
x64
alignment.h
assert.h
binary_find.h
bit_field.h
bit_util.h
cityhash.cpp
cityhash.h
CMakeLists.txt	shader_ir: Implement VOTE	2019-08-21 14:50:38 -03:00
color.h
common_funcs.h
common_paths.h
common_types.h
detached_tasks.cpp
detached_tasks.h
file_util.cpp
file_util.h
hash.h
hex_util.cpp
hex_util.h
lz4_compression.cpp
lz4_compression.h
math_util.h
memory_hook.cpp
memory_hook.h
microprofile.cpp
microprofile.h
microprofileui.h
misc.cpp
multi_level_queue.h
page_table.cpp
page_table.h
param_package.cpp
param_package.h
quaternion.h
ring_buffer.h
scm_rev.cpp.in
scm_rev.h
scope_exit.h
string_util.cpp
string_util.h
swap.h
telemetry.cpp
telemetry.h
thread_queue_list.h
thread.cpp
thread.h
threadsafe_queue.h
timer.cpp
timer.h
uint128.cpp
uint128.h
uuid.cpp
uuid.h
vector_math.h
web_result.h
zstd_compression.cpp
zstd_compression.h