VOPC_SDWA can also use arbitrary SGPR pairs on GFX9+.
Totals from 5607 (4.16% of 134913) affected shaders: (GFX10.3)
CodeSize:
42470760 ->
42452988 (-0.04%)
Instrs: 7943174 -> 7942883 (-0.00%)
Latency:
102887029 ->
102886305 (-0.00%); split: -0.00%, +0.00%
InvThroughput:
20454456 ->
20454338 (-0.00%); split: -0.00%, +0.00%
Copies: 376818 -> 376865 (+0.01%); split: -0.00%, +0.01%
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15408>
instr->operands[0].isFirstKillBeforeDef()) {
ctx.split_vectors[instr->operands[0].tempId()] = instr.get();
} else if (instr->isVOPC() && !instr->isVOP3()) {
- ctx.assignments[instr->definitions[0].tempId()].vcc = true;
+ if (!instr->isSDWA() || ctx.program->chip_class == GFX8)
+ ctx.assignments[instr->definitions[0].tempId()].vcc = true;
} else if (instr->isVOP2() && !instr->isVOP3()) {
if (instr->operands.size() == 3 && instr->operands[2].isTemp() &&
instr->operands[2].regClass().type() == RegType::sgpr)