From 7009e2683ebb917393d87639f549588f22c03a32 Mon Sep 17 00:00:00 2001 From: Francisco Jerez Date: Mon, 6 Jul 2015 18:55:26 +0300 Subject: [PATCH] i965/gen4-5: Enable 16-wide dispatch on shaders with control flow. This was probably disabled due to a combination of several bugs in the generator code (fixed earlier in this series) and a misunderstanding of the hardware spec. The documentation for most control flow instructions mentions among other restrictions: "Instruction compression is not allowed." This however doesn't have any implications on 16 wide not being supported, because none of the control flow instructions have multi-register operands (control flow instructions are not compressed on more recent hardware either, except maybe SNB's IF with inline compare). In fact Gen4-5 had 16-wide control flow masks and stacks, and the spec mentions in several places that control flow instructions push and pop 16 channels worth of data -- Otherwise there doesn't seem to be any indication that it shouldn't work. Causes no piglit regressions, and gives the following shader-db results on ILK: total instructions in shared programs: 4711384 -> 4711384 (0.00%) instructions in affected programs: 0 -> 0 helped: 0 HURT: 0 GAINED: 1215 LOST: 0 Reviewed-by: Matt Turner Reviewed-by: Kenneth Graunke --- src/mesa/drivers/dri/i965/brw_fs_nir.cpp | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp index 3ebc3a2c5e4..e01dfa88d52 100644 --- a/src/mesa/drivers/dri/i965/brw_fs_nir.cpp +++ b/src/mesa/drivers/dri/i965/brw_fs_nir.cpp @@ -417,18 +417,12 @@ fs_visitor::nir_emit_if(nir_if *if_stmt) bld.emit(BRW_OPCODE_ENDIF); - if (!try_replace_with_sel() && devinfo->gen < 6) { - no16("Can't support (non-uniform) control flow on SIMD16\n"); - } + try_replace_with_sel(); } void fs_visitor::nir_emit_loop(nir_loop *loop) { - if (devinfo->gen < 6) { - no16("Can't support (non-uniform) control flow on SIMD16\n"); - } - bld.emit(BRW_OPCODE_DO); nir_emit_cf_list(&loop->body); -- 2.30.2