From 378f9967710e9145f2a4f8eee89d87badbe0e6ea Mon Sep 17 00:00:00 2001 From: Ian Romanick Date: Mon, 18 Jun 2018 16:11:55 -0700 Subject: nir/opt_peephole_select: Don't peephole_select expensive math instructions On some GPUs, especially older Intel GPUs, some math instructions are very expensive. On those architectures, don't reduce flow control to a csel if one of the branches contains one of these expensive math instructions. This prevents a bunch of cycle count regressions on pre-Gen6 platforms with a later patch (intel/compiler: More peephole select for pre-Gen6). v2: Remove stray #if block. Noticed by Thomas. Signed-off-by: Ian Romanick Reviewed-by: Thomas Helland Reviewed-by: Lionel Landwerlin --- src/gallium/drivers/vc4/vc4_program.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'src/gallium/drivers/vc4/vc4_program.c') diff --git a/src/gallium/drivers/vc4/vc4_program.c b/src/gallium/drivers/vc4/vc4_program.c index 48d83061f9a..fb75c07e266 100644 --- a/src/gallium/drivers/vc4/vc4_program.c +++ b/src/gallium/drivers/vc4/vc4_program.c @@ -1591,7 +1591,7 @@ vc4_optimize_nir(struct nir_shader *s) NIR_PASS(progress, s, nir_opt_dce); NIR_PASS(progress, s, nir_opt_dead_cf); NIR_PASS(progress, s, nir_opt_cse); - NIR_PASS(progress, s, nir_opt_peephole_select, 8, true); + NIR_PASS(progress, s, nir_opt_peephole_select, 8, true, true); NIR_PASS(progress, s, nir_opt_algebraic); NIR_PASS(progress, s, nir_opt_constant_folding); NIR_PASS(progress, s, nir_opt_undef); -- cgit v1.2.3