Georg Lehmann c4f356faf4 aco: always use rtne for fquantize2f16 ... The SPIR-V spec says: If Value is positive with a magnitude too large to represent as a 16-bit floating-point value, the result is positive infinity. If Value is negative with a magnitude too large to represent as a 16-bit floating-point value, the result is negative infinity. This is only the case for rtne v_cvt_f16_f32 Reviewed-by: Rhys Perry <pendingchaos02@gmail.com> Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24617>		2023-08-11 12:37:23 +00:00
..
addrlib	ac/radv: decouple radv vulkan driver and compiler from gallium	2023-08-03 09:45:42 +00:00
ci	amd/ci: drop duplicate test expectations	2023-08-10 22:35:51 +00:00
common	ac/nir: handle more special cases in ac_nir_unpack_arg	2023-08-09 10:04:53 +00:00
compiler	aco: always use rtne for fquantize2f16	2023-08-11 12:37:23 +00:00
drm-shim	amd/drm-shim: use fixed-width types	2023-06-23 18:35:52 +00:00
llvm	nir: Drop nir_alu_src::{negate,abs}	2023-08-03 22:40:28 +00:00
registers	ac,radeonsi,winsyses: switch to SPDX-License-Identifier: MIT	2023-05-24 21:48:19 +00:00
vulkan	nir: add a filter cb to lower_io_to_scalar	2023-08-11 09:02:53 +00:00
meson.build	meson: build radeonsi with aco	2023-05-15 02:01:10 +00:00