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

nv50/ir: optimize shl(shr(a, c), c) to and(a, ~((1 << c) - 1))

Browse Source 
Following shader-db results on GK110:

total instructions in shared programs : 6141510 -> 6131491 (-0.16%)
total gprs used in shared programs    : 910187 -> 910157 (-0.00%)
total local used in shared programs   : 15328 -> 15328 (0.00%)

                local        gpr       inst      bytes
    helped           0          18         821         821
      hurt           0           0           0           0

Signed-off-by: Karol Herbst <nouveau@karolherbst.de>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
This commit is contained in:
Karol Herbst
2016-01-27 18:25:05 +01:00
committed by Ilia Mirkin
parent 089f605439
commit 978ae28ca2
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/gallium/drivers/nouveau/codegen/nv50_ir_peephole.cpp
+8
View File
@@ -1202,6 +1202,14 @@ ConstantFolding::opnd(Instruction *i, ImmediateValue &imm0, int s)
i->setSrc(1, bld.loadImm(NULL, imm0.reg.data.u32 + imm1.reg.data.u32));
}
break;
case OP_SHR:
if (si->src(1).getImmediate(imm1) && imm0.reg.data.u32 == imm1.reg.data.u32) {
bld.setPosition(i, false);
i->op = OP_AND;
i->setSrc(0, si->getSrc(0));
i->setSrc(1, bld.loadImm(NULL, ~((1 << imm0.reg.data.u32) - 1)));
}
break;
case OP_MUL:
int muls;
if (isFloatType(si->dType))