From 3cd38b68987f28536abd218fd62de5dc38c14aa1 Mon Sep 17 00:00:00 2001 From: Iago Toral Quiroga Date: Tue, 6 Sep 2016 08:56:05 +0200 Subject: i965/vec4: prevent spilling of DOUBLE_TO_SINGLE destination FROM_DOUBLE opcodes are setup so that they use a dst register with a size of 2 even if they only produce a single-precison result (this is so that the opcode can use the larger register to produce a 64-bit aligned intermediary result as required by the hardware during the conversion process). This creates a problem for spilling though, because when we attempt to emit a spill for the dst we see a 32-bit destination and emit a scratch write that allocates a single spill register, making the intermediary writes go beyond the size of the allocation. Prevent this by avoiding to spill the destination register of these opcodes. Alternatively, we can avoid this by splitting the opcode in two: one that produces a 64-bit aligned result and one that takes the 64-bit aligned result as input and produces a 32-bit result from it. Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'src') diff --git a/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp b/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp index 79fd15b12bb..2e5bc79b485 100644 --- a/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp +++ b/src/mesa/drivers/dri/i965/brw_vec4_reg_allocate.cpp @@ -436,6 +436,18 @@ vec4_visitor::evaluate_spill_costs(float *spill_costs, bool *no_spill) if (type_sz(inst->dst.type) == 8 && inst->exec_size != 8) no_spill[inst->dst.nr] = true; + /* FROM_DOUBLE opcodes are setup so that they use a dst register + * with a size of 2 even if they only produce a single-precison + * result (this is so that the opcode can use the larger register to + * produce a 64-bit aligned intermediary result as required by the + * hardware during the conversion process). This creates a problem for + * spilling though, because when we attempt to emit a spill for the + * dst we see a 32-bit destination and emit a scratch write that + * allocates a single spill register. + */ + if (inst->opcode == VEC4_OPCODE_FROM_DOUBLE) + no_spill[inst->dst.nr] = true; + /* We can't spill registers that mix 32-bit and 64-bit access (that * contain 64-bit data that is operated on via 32-bit instructions) */ -- cgit v1.2.3