From 9ebc00f32ee434d4ca70f0fc562fc4df62e3859d Mon Sep 17 00:00:00 2001 From: Jason Ekstrand Date: Thu, 28 Dec 2017 19:53:36 -0800 Subject: i965: Enable nir_opt_idiv_const for 32 and 64-bit integers The pass should work for all bit sizes but it's less clear that the extra instructions are worth it on small integers. Also, the hardware doesn't do mul_high on anything other than 32-bit integers and, absent any decent mechanism for testing the pass on 8 and 16-bit types, it's probably best to just leave it disabled for now. Shader-db results on Sky Lake: total instructions in shared programs: 15105795 -> 15111403 (0.04%) instructions in affected programs: 72774 -> 78382 (7.71%) helped: 0 HURT: 265 Note that hurt here actually means helped because we're getting rid of integer quotient operations (which are a send on some platforms!) and replacing them with fairly cheap ALU ops. Reviewed-by: Ian Romanick ian.d.romanick@intel.com --- src/intel/compiler/brw_nir.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'src/intel/compiler/brw_nir.c') diff --git a/src/intel/compiler/brw_nir.c b/src/intel/compiler/brw_nir.c index 2723ab6d4fb..44a720c6506 100644 --- a/src/intel/compiler/brw_nir.c +++ b/src/intel/compiler/brw_nir.c @@ -570,6 +570,7 @@ brw_nir_optimize(nir_shader *nir, const struct brw_compiler *compiler, OPT(nir_opt_cse); OPT(nir_opt_peephole_select, 0); OPT(nir_opt_intrinsics); + OPT(nir_opt_idiv_const, 32); OPT(nir_opt_algebraic); OPT(nir_opt_constant_folding); OPT(nir_opt_dead_cf); @@ -679,7 +680,8 @@ brw_preprocess_nir(const struct brw_compiler *compiler, nir_shader *nir) */ OPT(nir_lower_int64, nir_lower_imul64 | nir_lower_isign64 | - nir_lower_divmod64); + nir_lower_divmod64 | + nir_lower_imul_high64); nir = brw_nir_optimize(nir, compiler, is_scalar, true); -- cgit v1.2.3