From 6049745b132c29fb62d3ab19e343f34311432e70 Mon Sep 17 00:00:00 2001 From: Samuel Pitoiset Date: Thu, 18 Jul 2019 15:51:27 +0200 Subject: [PATCH] ac/nir: do not clamp shadow reference on GFX10 RadeonSI only uses Z32_FLOAT_CLAMP for upgraded depth textures on GFX10 and RADV doesn't promotes Z16 or Z24. Signed-off-by: Samuel Pitoiset Reviewed-by: Bas Nieuwenhuizen --- src/amd/common/ac_nir_to_llvm.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c index f69e02f..ec79e5f 100644 --- a/src/amd/common/ac_nir_to_llvm.c +++ b/src/amd/common/ac_nir_to_llvm.c @@ -3805,12 +3805,16 @@ static void visit_tex(struct ac_nir_context *ctx, nir_tex_instr *instr) /* TC-compatible HTILE on radeonsi promotes Z16 and Z24 to Z32_FLOAT, * so the depth comparison value isn't clamped for Z16 and - * Z24 anymore. Do it manually here. + * Z24 anymore. Do it manually here for GFX8-9; GFX10 has an explicitly + * clamped 32-bit float format. * * It's unnecessary if the original texture format was * Z32_FLOAT, but we don't know that here. */ - if (args.compare && ctx->ac.chip_class >= GFX8 && ctx->abi->clamp_shadow_reference) + if (args.compare && + ctx->ac.chip_class >= GFX8 && + ctx->ac.chip_class <= GFX9 && + ctx->abi->clamp_shadow_reference) args.compare = ac_build_clamp(&ctx->ac, ac_to_float(&ctx->ac, args.compare)); /* pack derivatives */ -- 2.7.4