KonstantinSeurer
/
mesa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

nir: Recognize open-coded extract_u8. 

Two shaders that appear in Unigine benchmarks (Heaven and Valley) unpack
three bytes from an integer and convert each into a float:

   float((val >> 16u) & 0xffu)
   float((val >>  8u) & 0xffu)
   float((val >>  0u) & 0xffu)

Instead of shifting, masking, and type converting like this:

   shr(8)          g15<1>UD        g25<8,8,1>UD    0x00000010UD
   and(8)          g16<1>UD        g15<8,8,1>UD    0x000000ffUD
   mov(8)          g17<1>F         g16<8,8,1>UD

   shr(8)          g18<1>UD        g25<8,8,1>UD    0x00000008UD
   and(8)          g19<1>UD        g18<8,8,1>UD    0x000000ffUD
   mov(8)          g20<1>F         g19<8,8,1>UD

   and(8)          g21<1>UD        g25<8,8,1>UD    0x000000ffUD
   mov(8)          g22<1>F         g21<8,8,1>UD

i965 can simply extract a byte and convert to float in a single
instruction:

   mov(8)          g17<1>F         g25.2<32,8,4>UB
   mov(8)          g20<1>F         g25.1<32,8,4>UB
   mov(8)          g22<1>F         g25.0<32,8,4>UB

This patch implements the first step: recognizing byte extraction. A
later patch will optimize out the conversion to float.

   instructions in affected programs: 28568 -> 27450 (-3.91%)
   helped: 7

   cycles in affected programs: 210076 -> 203144 (-3.30%)
   helped: 7

This patch decreases the number of instructions in the two Unigine
programs by:

 #1721: 4520 -> 4374 instructions (-3.23%)
 #1706: 3752 -> 3582 instructions (-4.53%)

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
This commit is contained in:
Matt Turner 2016-01-21 09:09:48 -08:00
parent 01e92e7010
commit 76289fbfa8
1 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/compiler/nir/nir_opt_algebraic.py
View File

@ -162,6 +162,7 @@ optimizations = [
(('ishr', a, 0), a), (('ishr', a, 0), a),
(('ushr', 0, a), 0), (('ushr', 0, a), 0),
(('ushr', a, 0), a), (('ushr', a, 0), a),
(('iand', 0xff, ('ushr', a, 24)), ('ushr', a, 24)),
# Exponential/logarithmic identities # Exponential/logarithmic identities
(('fexp2', ('flog2', a)), a), # 2^lg2(a) = a (('fexp2', ('flog2', a)), a), # 2^lg2(a) = a
(('flog2', ('fexp2', a)), a), # lg2(2^a) = a (('flog2', ('fexp2', a)), a), # lg2(2^a) = a
@ -213,6 +214,12 @@ optimizations = [
(('f2i', ('ftrunc', a)), ('f2i', a)), (('f2i', ('ftrunc', a)), ('f2i', a)),
(('f2u', ('ftrunc', a)), ('f2u', a)), (('f2u', ('ftrunc', a)), ('f2u', a)),
# Byte extraction
(('ushr', a, 24), ('extract_u8', a, 3), '!options->lower_extract_byte'),
(('iand', 0xff, ('ushr', a, 16)), ('extract_u8', a, 2), '!options->lower_extract_byte'),
(('iand', 0xff, ('ushr', a, 8)), ('extract_u8', a, 1), '!options->lower_extract_byte'),
(('iand', 0xff, a), ('extract_u8', a, 0), '!options->lower_extract_byte'),
# Subtracts # Subtracts
(('fsub', a, ('fsub', 0.0, b)), ('fadd', a, b)), (('fsub', a, ('fsub', 0.0, b)), ('fadd', a, b)),
(('isub', a, ('isub', 0, b)), ('iadd', a, b)), (('isub', a, ('isub', 0, b)), ('iadd', a, b)),