From: Eric Anholt <eric@anholt.net>
Date: Tue, 10 May 2011 19:55:12 +0000 (-0700)
Subject: i965/fs: Add support for "if" statements in 16-wide mode on gen6+.
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=136eb2bde769713b100351ff96bceb970f068c0a;p=mesa.git

i965/fs: Add support for "if" statements in 16-wide mode on gen6+.

It turns out there's nothing in the hardware preventing this.  It
appears that it ought to work on pre-gen6 as well, but just produces
GPU hangs.

Improves glbenchmark Egypt framerate 4.4% +/- 0.3% (n=3), and Pro by
2.6% +/- 0.6% (n=3).

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
---

diff --git a/src/mesa/drivers/dri/i965/brw_eu_emit.c b/src/mesa/drivers/dri/i965/brw_eu_emit.c
index 007f58c341c..2d41302d15a 100644
--- a/src/mesa/drivers/dri/i965/brw_eu_emit.c
+++ b/src/mesa/drivers/dri/i965/brw_eu_emit.c
@@ -1003,7 +1003,11 @@ gen6_IF(struct brw_compile *p, uint32_t conditional,
    insn = next_insn(p, BRW_OPCODE_IF);
 
    brw_set_dest(p, insn, brw_imm_w(0));
-   insn->header.execution_size = BRW_EXECUTE_8;
+   if (p->compressed) {
+      insn->header.execution_size = BRW_EXECUTE_16;
+   } else {
+      insn->header.execution_size = BRW_EXECUTE_8;
+   }
    insn->bits1.branch_gen6.jump_count = 0;
    brw_set_src0(p, insn, src0);
    brw_set_src1(p, insn, src1);
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 018a16e4322..5232a7f77af 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -1859,7 +1859,7 @@ fs_visitor::visit(ir_if *ir)
 {
    fs_inst *inst;
 
-   if (c->dispatch_width == 16) {
+   if (intel->gen != 6 && c->dispatch_width == 16) {
       fail("Can't support (non-uniform) control flow on 16-wide\n");
    }
 
@@ -3872,7 +3872,7 @@ fs_visitor::generate_code()
 	    assert(intel->gen == 6);
 	    gen6_IF(p, inst->conditional_mod, src[0], src[1]);
 	 } else {
-	    brw_IF(p, BRW_EXECUTE_8);
+	    brw_IF(p, c->dispatch_width == 16 ? BRW_EXECUTE_16 : BRW_EXECUTE_8);
 	 }
 	 if_depth_in_loop[loop_stack_depth]++;
 	 break;