On Thursday, August 28, 2014 08:10:31 PM Matt Turner wrote:
> Despite what the Sandybridge PRM says, ENDIF has Jump Count in <dst>,
> not JIP in <src1>. (The same mistake appears about WHILE as well).
> ---
> src/mesa/drivers/dri/i965/brw_eu_emit.c | 11 +++++++----
> 1 file changed, 7 insertions(+), 4 deletions(-)
>
> diff --git a/src/mesa/drivers/dri/i965/brw_eu_emit.c
> b/src/mesa/drivers/dri/i965/brw_eu_emit.c
> index 39f94e9..937257b 100644
> --- a/src/mesa/drivers/dri/i965/brw_eu_emit.c
> +++ b/src/mesa/drivers/dri/i965/brw_eu_emit.c
> @@ -2557,12 +2557,15 @@ brw_set_uip_jip(struct brw_compile *p)
> assert(brw_inst_jip(brw, insn) != 0);
> break;
>
> - case BRW_OPCODE_ENDIF:
> - if (block_end_offset == 0)
> - brw_inst_set_jip(brw, insn, 1 * br);
> + case BRW_OPCODE_ENDIF: {
> + int32_t jump = (block_end_offset == 0) ?
> + 1 * br : (block_end_offset - offset) / scale;
> + if (brw->gen >= 7)
> + brw_inst_set_jip(brw, insn, jump);
> else
> - brw_inst_set_jip(brw, insn, (block_end_offset - offset) / scale);
> + brw_inst_set_gen6_jump_count(brw, insn, jump);
> break;
> + }
>
> case BRW_OPCODE_HALT:
> /* From the Sandy Bridge PRM (volume 4, part 2, section 8.3.19):
> Cc: "10.3" <mesa-sta...@lists.freedesktop.org> Reviewed-by: Kenneth Graunke <kenn...@whitecape.org>
signature.asc
Description: This is a digitally signed message part.
_______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
