If an element has very long interval, we don't want to put it into a vector as it will add more pressure to the register allocation.
With this patch, it can reduce more than 20% spill registers for luxmark's median scene benchmark(from 288 to 224). Signed-off-by: Zhigang Gong <[email protected]> --- backend/src/backend/gen_reg_allocation.cpp | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/backend/src/backend/gen_reg_allocation.cpp b/backend/src/backend/gen_reg_allocation.cpp index 4e276c3..c282b36 100644 --- a/backend/src/backend/gen_reg_allocation.cpp +++ b/backend/src/backend/gen_reg_allocation.cpp @@ -271,9 +271,12 @@ namespace gbe // case 1: the register is not already in a vector, so it can stay in this // vector. Note that local IDs are *non-scalar* special registers but will // require a MOV anyway since pre-allocated in the CURBE + // If an element has very long interval, we don't want to put it into a + // vector as it will add more pressure to the register allocation. if (it == vectorMap.end() && ctx.sel->isScalarOrBool(reg) == false && - ctx.isSpecialReg(reg) == false) + ctx.isSpecialReg(reg) == false && + (intervals[reg].maxID - intervals[reg].minID) < 2048) { const VectorLocation location = std::make_pair(vector, regID); this->vectorMap.insert(std::make_pair(reg, location)); -- 1.8.3.2 _______________________________________________ Beignet mailing list [email protected] http://lists.freedesktop.org/mailman/listinfo/beignet
