From e9a9d441f0b1a0293e0901d0f6b99a946e51f6f4 Mon Sep 17 00:00:00 2001 From: Kenneth Graunke Date: Mon, 4 Aug 2014 00:06:05 -0700 Subject: [PATCH] i965: Set ExecSize to 16 for loop instructions in SIMD16 shaders. Previously, we explicitly set the execution size to BRW_EXECUTE_8 and disabled compression for loop instructions. I can't imagine how this could be correct in SIMD16 mode. Looking at the history, it appears that this code has used BRW_EXECUTE_8 since 2007, when we had a SIMD8 backend that supported control flow and a separate SIMD16 backend that didn't. Presumably, when we added SIMD16 support for shaders with control flow, we simply neglected to update it. Note that Gen4-5 don't support SIMD16 on shaders with control flow. This might be a candidate for stable, but would need to be rewritten completely due to the brw_inst API changes in master. Signed-off-by: Kenneth Graunke Reviewed-by: Matt Turner --- src/mesa/drivers/dri/i965/brw_eu_emit.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_eu_emit.c b/src/mesa/drivers/dri/i965/brw_eu_emit.c index 3be4449b4e0..e894abdaec0 100644 --- a/src/mesa/drivers/dri/i965/brw_eu_emit.c +++ b/src/mesa/drivers/dri/i965/brw_eu_emit.c @@ -1526,7 +1526,8 @@ brw_BREAK(struct brw_compile *p) p->if_depth_in_loop[p->loop_stack_depth]); } brw_inst_set_qtr_control(brw, insn, BRW_COMPRESSION_NONE); - brw_inst_set_exec_size(brw, insn, BRW_EXECUTE_8); + brw_inst_set_exec_size(brw, insn, p->compressed ? BRW_EXECUTE_16 + : BRW_EXECUTE_8); return insn; } @@ -1546,9 +1547,9 @@ brw_CONT(struct brw_compile *p) brw_inst_set_gen4_pop_count(brw, insn, p->if_depth_in_loop[p->loop_stack_depth]); } - brw_inst_set_qtr_control(brw, insn, BRW_COMPRESSION_NONE); - brw_inst_set_exec_size(brw, insn, BRW_EXECUTE_8); + brw_inst_set_exec_size(brw, insn, p->compressed ? BRW_EXECUTE_16 + : BRW_EXECUTE_8); return insn; } @@ -1664,7 +1665,8 @@ brw_WHILE(struct brw_compile *p) brw_set_src1(p, insn, brw_imm_ud(0)); brw_inst_set_jip(brw, insn, br * (do_insn - insn)); - brw_inst_set_exec_size(brw, insn, BRW_EXECUTE_8); + brw_inst_set_exec_size(brw, insn, p->compressed ? BRW_EXECUTE_16 + : BRW_EXECUTE_8); } else if (brw->gen == 6) { insn = next_insn(p, BRW_OPCODE_WHILE); do_insn = get_inner_do_insn(p); @@ -1674,7 +1676,8 @@ brw_WHILE(struct brw_compile *p) brw_set_src0(p, insn, retype(brw_null_reg(), BRW_REGISTER_TYPE_D)); brw_set_src1(p, insn, retype(brw_null_reg(), BRW_REGISTER_TYPE_D)); - brw_inst_set_exec_size(brw, insn, BRW_EXECUTE_8); + brw_inst_set_exec_size(brw, insn, p->compressed ? BRW_EXECUTE_16 + : BRW_EXECUTE_8); } else { if (p->single_program_flow) { insn = next_insn(p, BRW_OPCODE_ADD); -- 2.30.2