On Tue, Jun 8, 2010 at 5:53 AM, bugzilla-daemon@freedesktop.org wrote:
https://bugs.freedesktop.org/show_bug.cgi?id=27901
--- Comment #18 from Andre Maasikas amaasikas@gmail.com 2010-06-08 05:53:36 PDT --- dont' have much net this week to review/test:( but i'm ok with it if you make last mul conditional on r700 as it has -1..1 range it seems, also amd shader analyzer gives this difference:
RV610 hd2400
; -------- Disassembly -------------------- 00 ALU: ADDR(32) CNT(8) 0 y: MULADD R123.y, R0.x, (0x3E22F983, 0.1591549367f).x, 0.5 z: MOV R0.z, 0.0f w: MOV R0.w, 1.0f 1 x: FRACT ____, PV0.y 2 z: MULADD R123.z, PV1.x, (0x40C90FDB, 6.283185482f).y, -(0x40490FDB, 3.141592741f).x 3 t: SIN R0.x, PV2.z 01 EXP_DONE: PIX0, R0.xzzw END_OF_PROGRAM
4870 RV770 ; -------- Disassembly -------------------- 00 ALU: ADDR(32) CNT(10) 0 y: MOV R0.y, 0.0f z: MOV R0.z, 1.0f w: MULADD R123.w, R0.x, (0x3E22F983, 0.1591549367f).x, 0.5 1 y: FRACT ____, PV0.w 2 x: MULADD R123.x, PV1.y, (0x40C90FDB, 6.283185482f).y, -(0x40490FDB, 3.141592741f).x 3 z: MUL ____, PV2.x, (0x3E22F983, 0.1591549367f).x 4 t: SIN R0.x, PV3.z 01 EXP_DONE: PIX0, R0.xyyz END_OF_PROGRAM
-- Configure bugmail: https://bugs.freedesktop.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are the assignee for the bug. _______________________________________________ dri-devel mailing list dri-devel@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/dri-devel
This is very very strange that amd would change the instruction. I wonder if it is a bug in their code.... Perhaps we need someone with an r700 to run the sin and cos tests in piglit . The proposed patch passes on my rs780 (rv610) .