This is the error text from the rx9070xt....

Stderr output
<core_client_version>7.24.1</core_client_version>
<![CDATA[
<stderr_txt>
2026-09-07 11:18:28 (2820): wrapper: running prpll.exe (-d 0)
2026-09-07 11:18:28 (2820): wrapper: created child process 13852
20260907 11:18:28 PRPLL v8.0-2-g8fb01aa starting
20260907 11:18:28 config: -d 0
20260907 11:18:28 device 0, OpenCL 3679.0 (PAL,LC), AMD Radeon RX 9070 XT, unique id ''
20260907 11:18:28 83824649 No FFTs found in tune.txt that can handle 83824649. Consider tuning with -tune
20260907 11:18:28 83824649 config:
20260907 11:18:28 83824649 Using CARRY64
20260907 11:18:28 83824649 FFT: 2M 4:1K:4:256:101 (39.97 bpw)
20260907 11:18:28 83824649 LL loaded @ 0 : 0000000000000004
20260907 11:18:29 83824649 In file included from C:\Users\renix\AppData\Local\Temp\comgr-e3340e\input\CompileSource:1:
In file included from C:\Users\renix\AppData\Local\Temp\comgr-e3340e\include\fftp.cl:5:
In file included from C:\Users\renix\AppData\Local\Temp\comgr-e3340e\include\fftwidth.cl:18:
C:\Users\renix\AppData\Local\Temp\comgr-e3340e\include\fftbase.cl:1136:8: error: assigning to '__private F2' (aka '__private float2') from incompatible type 'ulong2' (vector of 2 'ulong' values)
1136 | base = U2(fma(a, -w.y, w.x), fma(a, w.x, -w.y));
| ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1 error generated.
Error: Failed to compile source (from CL or HIP source to LLVM IR).

20260907 11:18:29 83824649 Compiling 'fftp.cl' error COMPILE_PROGRAM_FAILURE (-15) (args -cl-finite-math-only -cl-std=CL2.0 -DEXP=83824649ull -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=4u -DCARRY_LEN=8u -DNW=4u -DNH=4u -DAMDGPU=1 -DCARRY64=1 -DFFT_VARIANT=101u -DMAXBPW=4750u -DWEIGHT_STEP=0.020511601490304197 -DIWEIGHT_STEP=-0.020099332002056696 -DTAILT=U2(-7.52981578e-05f,0.0122715384f) -DTRIG_SCALE=9 -DTRIG_SIN={6.6579027251980952e-07,3.7209369054580932e-23,-4.9188217704570848e-20,1.0901995091303198e-33,-1.1506191102407305e-47,7.0839240359575376e-62,-2.8545227803597818e-76,8.0307778151820938e-91,} -DTRIG_COS={1,-2.2163834349100114e-13,8.1872592175725296e-27,-1.209740380477418e-40,9.5758876440886212e-55,-4.7164085661095887e-69,1.5838111582820031e-83,-3.830342691138796e-98,} -DTAILTGF31=U2(509684486u,293249438u) -DTAILTGF61=U2(249938719029223731ull,1245372627562045535ull) -DFFT_TYPE=4 -DWordSize=8u -DDISTGF31=819200u -DDISTWTRIGGF31=2560u -DDISTMTRIGGF31=768u -DDISTHTRIGGF31=131776u -DDISTGF61=1638400ull -DDISTWTRIGGF61=3072ull -DDISTMTRIGGF61=1792ull -DDISTHTRIGGF61=263040ull -DFRAC_BPW_HI=4169156607u -DFRAC_BPW_LO=4294967295u -DFFT_FP64=0 -DFFT_FP32=1 -DNTT_GF31=1 -DNTT_GF61=1 )
20260907 11:18:29 83824649 Can't compile fftp.cl
20260907 11:18:29 Exception "Can't compile fftp.cl"
20260907 11:18:29 Bye
2026-09-07 11:18:29 (2820): prpll.exe exited; CPU time 0.015625
2026-09-07 11:18:29 (2820): called boinc_finish(0)

</stderr_txt>
<message>
upload failure: <file_xfer_error>
<file_name>LL-dc_83.79-83.83M_wu_388_12_0</file_name>
<error_code>-240 (stat() failed)</error_code>
</file_xfer_error>
</message>
]]>

So just going to crunch llr with nvidia only. :-)

Adrenalin 26.9.1 for the 9070xt. The TF units crunch fine for both thr 9070 and 7900gre. But fail for both gpu's on llr. One of the earlier llr units failed with the previous adrenalin release (gre).