From 3abe68b8282496688186157b51da5600ac540906 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Wed, 14 Sep 2016 23:02:38 +0200 Subject: [PATCH] nv50/ir: teach insnCanLoad() about SHLADD Commutativity is not allowed with SHLADD, but src2 can accept loads. To allow the load propagation pass to do its job, add a special case like for SUCLAMP because src1 is always an immediate. This IMAD to SHLADD optimization helps a bunch of shaders from Tomb Raider, Victor Vran, UE4 demos (+15% perf with Elemental) and Shadow Warrior. GF100/GK104: total instructions in shared programs :2838045 -> 2834712 (-0.12%) total gprs used in shared programs :396684 -> 396386 (-0.08%) total local used in shared programs :34416 -> 34416 (0.00%) local gpr inst bytes helped 0 326 1105 1105 hurt 0 55 3 3 Signed-off-by: Samuel Pitoiset Reviewed-by: Ilia Mirkin --- src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp index 86060653993..2d1f1b45247 100644 --- a/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp +++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_target_nvc0.cpp @@ -334,6 +334,8 @@ TargetNVC0::insnCanLoad(const Instruction *i, int s, if (i->src(k).getFile() == FILE_IMMEDIATE) { if (k == 2 && i->op == OP_SUCLAMP) // special case continue; + if (k == 1 && i->op == OP_SHLADD) // special case + continue; if (i->getSrc(k)->reg.data.u64 != 0) return false; } else -- 2.30.2