[Bug 101562] Fetching from imageBuffer creates very poor GEN assembly

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Fri Jun 23 07:30:47 UTC 2017


https://bugs.freedesktop.org/show_bug.cgi?id=101562

            Bug ID: 101562
           Summary: Fetching from imageBuffer creates very poor GEN
                    assembly
           Product: Mesa
           Version: 17.1
          Hardware: x86-64 (AMD64)
                OS: Linux (All)
            Status: NEW
          Severity: normal
          Priority: medium
         Component: Drivers/DRI/i965
          Assignee: intel-3d-bugs at lists.freedesktop.org
          Reporter: kevin.rogovin at intel.com
        QA Contact: intel-3d-bugs at lists.freedesktop.org

Created attachment 132153
  --> https://bugs.freedesktop.org/attachment.cgi?id=132153&action=edit
tarball of results: .shader.txt is input shader, .asm.txt is outout of
INTEL_DEBUG=fs

If one uses an imageBuffer to fetch values and add them in either of the forms:

 value = start_value + get_value(0) + get_value(1) + ... 
or
 value = ((((((...(start_value + get_value(0)) + get_value(1)) + ... )

then the generated assembly is quite poor. It reserves O(n) registers (where n
is the number of constants to fetch) at shader start, with those values placed
into the registers having a large number of duplicates.

However, if the shader is:

 value = start_value;
 value += get_value(0);
 value += get_value(1); 

or if the constants are fetched though other means (UBO, TBO, SSBO) then the
generated assembly is fine. This is in spite of the fact that the above is
equivalent to the 2nd form of a one line add.

Attached is a battery of machine generated shaders and the output of
INTEL_DEBUG=fs when compiling such shaders with a matching, but trivial, vertex
shader.

-- 
You are receiving this mail because:
You are the assignee for the bug.
You are the QA Contact for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-3d-bugs/attachments/20170623/9460486c/attachment-0001.html>


More information about the intel-3d-bugs mailing list