From: Karol Herbst <karolher...@gmail.com>
This helps with the PostRALoadPropagation pass moving long immediates into
FMA/MAD instructions.
changes in shader-db:
total instructions in shared programs : 5894114 -> 5886074 (-0.14%)
total gprs used in shared programs : 666558 -> 666563 (0.00%)
total shared used in shared programs : 520416 -> 520416 (0.00%)
total local used in shared programs : 53524 -> 53524 (0.00%)
total bytes used in shared programs : 54006744 -> 53932472 (-0.14%)
local shared gpr inst bytes
helped 0 0 2 4192 4192
hurt 0 0 7 9 9
Signed-off-by: Karol Herbst <karolher...@gmail.com>
---
src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp | 30 ++++++++++++++--------
1 file changed, 20 insertions(+), 10 deletions(-)
diff --git a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
index 3a0e56e1385..aeaf1ebe8f0 100644
--- a/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
+++ b/src/gallium/drivers/nouveau/codegen/nv50_ir_ra.cpp
@@ -1466,17 +1466,27 @@ GCRA::allocateRegisters(ArrayList& insns)
nodes[i].init(regs, lval);
RIG.insert(&nodes[i]);
- if (lval->inFile(FILE_GPR) && lval->getInsn() != NULL &&
- prog->getTarget()->getChipset() < 0xc0) {
+ if (lval->inFile(FILE_GPR) && lval->getInsn() != NULL) {
Instruction *insn = lval->getInsn();
- if (insn->op == OP_MAD || insn->op == OP_FMA || insn->op == OP_SAD)
- // Short encoding only possible if they're all GPRs, no need to
- // affect them otherwise.
- if (insn->flagsDef < 0 &&
- insn->src(0).getFile() == FILE_GPR &&
- insn->src(1).getFile() == FILE_GPR &&
- insn->src(2).getFile() == FILE_GPR)
-
nodes[i].addRegPreference(getNode(insn->getSrc(2)->asLValue()));
+ if (insn->op != OP_MAD && insn->op != OP_FMA && insn->op != OP_SAD)
+ continue;
+ // Short encoding or load propagate immediates only possible if
+ // they're all GPRs, no need to affect them otherwise.
+ if (insn->flagsDef >= 0 ||
+ insn->src(0).getFile() != FILE_GPR ||
+ insn->src(1).getFile() != FILE_GPR ||
+ insn->src(2).getFile() != FILE_GPR)
+ continue;
+ // for nvc0+ we can loadpropagate limms only if we have
+ // dest == src2 reg id. Using getImmediate here is fine because
+ // we only set a reg preference and leave the immediate alone.
+ ImmediateValue imm;
+ if (prog->getTarget()->getChipset() >= 0xc0 &&
+ !insn->src(0).getImmediate(imm) &&
+ !insn->src(1).getImmediate(imm))
+ continue;
+
+ nodes[i].addRegPreference(getNode(insn->getSrc(2)->asLValue()));
}
}
}
--
2.14.3
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
