diff options
author | Eric Anholt <eric@anholt.net> | 2013-11-12 15:33:27 -0800 |
---|---|---|
committer | Eric Anholt <eric@anholt.net> | 2014-01-17 12:58:43 -0800 |
commit | 746e3e3b3ad20a29ee6de64d663d2dc11deac06e (patch) | |
tree | f554790b43bbcc7bdfe41cc8a2a94ae3c4c17cce /src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp | |
parent | 26a3bf5c726199d7664d5878ef1f73592e55caa7 (diff) | |
download | external_mesa3d-746e3e3b3ad20a29ee6de64d663d2dc11deac06e.zip external_mesa3d-746e3e3b3ad20a29ee6de64d663d2dc11deac06e.tar.gz external_mesa3d-746e3e3b3ad20a29ee6de64d663d2dc11deac06e.tar.bz2 |
i965: Replace 8-wide and 16-wide with SIMD8 and SIMD16.
Those are the terms used in the docs, and think "n-wide" was something I
just happened to say. Note that shader-db needs updating for the
INTEL_DEBUG=fs parsing.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp')
-rw-r--r-- | src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp b/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp index baf67fb..a61bbab 100644 --- a/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp +++ b/src/mesa/drivers/dri/i965/brw_schedule_instructions.cpp @@ -431,8 +431,8 @@ public: * Returns how many cycles it takes the instruction to issue. * * Instructions in gen hardware are handled one simd4 vector at a time, - * with 1 cycle per vector dispatched. Thus 8-wide pixel shaders take 2 - * cycles to dispatch and 16-wide (compressed) instructions take 4. + * with 1 cycle per vector dispatched. Thus SIMD8 pixel shaders take 2 + * cycles to dispatch and SIMD16 (compressed) instructions take 4. */ virtual int issue_time(backend_instruction *inst) = 0; @@ -1157,7 +1157,7 @@ fs_instruction_scheduler::choose_instruction_to_schedule() } else { /* Before register allocation, we don't care about the latencies of * instructions. All we care about is reducing live intervals of - * variables so that we can avoid register spilling, or get 16-wide + * variables so that we can avoid register spilling, or get SIMD16 * shaders which naturally do a better job of hiding instruction * latency. */ |