From d358af050352d5feacd5ef38ff8e1341a47067e9 Mon Sep 17 00:00:00 2001 From: Christopher Egert Date: Fri, 15 May 2020 16:41:15 +0200 Subject: [PATCH] radv: use util_float_to_half_rtz Since commit 8b8af6d398a94cb07015c695fdfdb5c157aa72cf there is a performance regression in dirt 4 on picasso APUs. The game ends up feeding a large value into this which overflows on the conversion to 16bit float. With the old implementation (which now lives in util_float_to_half_rtz) it would be clamped to inf-1, while the new one returns inf. This causes a performance hit somehow at some point down the line. Reviewed-by: Bas Nieuwenhuizen Fixes: 8b8af6d398a "gallium/util: Switch util_float_to_half to _mesa_float_to_half()'s impl." Part-of: (cherry picked from commit 78615dcca19699737bf9cbc784b66d9ea966bcc0) --- .pick_status.json | 2 +- src/amd/vulkan/radv_formats.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.pick_status.json b/.pick_status.json index 0658d22e8f0..c9a20deac2d 100644 --- a/.pick_status.json +++ b/.pick_status.json @@ -1822,7 +1822,7 @@ "description": "radv: use util_float_to_half_rtz", "nominated": true, "nomination_type": 1, - "resolution": 0, + "resolution": 1, "master_sha": null, "because_sha": "8b8af6d398a94cb07015c695fdfdb5c157aa72cf" }, diff --git a/src/amd/vulkan/radv_formats.c b/src/amd/vulkan/radv_formats.c index a790459c900..badfcc4f72f 100644 --- a/src/amd/vulkan/radv_formats.c +++ b/src/amd/vulkan/radv_formats.c @@ -1060,7 +1060,7 @@ bool radv_format_pack_clear_color(VkFormat format, if (channel->size == 32) { memcpy(&v, &value->float32[c], 4); } else if(channel->size == 16) { - v = util_float_to_half(value->float32[c]); + v = util_float_to_half_rtz(value->float32[c]); } else { fprintf(stderr, "failed to fast clear for unhandled float size in format %d\n", format); return false;