Task 60794054
| Name | LL-dc_84.35-84.41M_wu_464_1 |
| Workunit | 54519663 |
| Created | 11 Nov 2026, 12:26:04 UTC |
| Sent | 11 Nov 2026, 13:26:20 UTC |
| Report deadline | 24 Nov 2026, 13:26:20 UTC |
| Received | 11 Nov 2026, 13:36:08 UTC |
| Server state | Over |
| Outcome | Computation error |
| Client state | Compute error |
| Exit status | 195 (0xc3) EXIT_CHILD_FAILED |
| Computer ID | 257776 |
| Run time | 3 sec |
| CPU time |
|
| Validate state | Invalid |
| Credit | 0.00 |
| Device peak FLOPS | 4,114.35 GFLOPS |
| Application version | LL - dc v0.14 (opencl_ati_200) |
| Peak disk usage | 2.13 MB |
Stderr output
<core_client_version>8.2.15</core_client_version>
<![CDATA[
<message>
process exited with code 195 (0xc3, -61)</message>
<stderr_txt>
2026-11-11 08:29:03 (1395833): wrapper (8.3.26019): starting
2026-11-11 08:29:03 (1395833): wrapper: running ./prpll (-d 0)
2026-11-11 08:29:03 (1395833): wrapper: created child process 1395835
=== Rusticl warning: Patched Mesa libclc not detected. Upstream libclc may contain known bugs or breaking changes and isn't guaranteed to work reliably. Please visit https://gitlab.freedesktop.org/karolherbst/mesa-libclc for more information. ===
20261111 08:29:03 PRPLL v8 Linux_x64 2026-10-17 starting
20261111 08:29:03 config: -d 0
20261111 08:29:04 device 0, OpenCL 26.2.6-arch3.1, , unique id ''
20261111 08:29:04 No FFTs found in tune.txt that can handle 84410107. Consider tuning with -tune
20261111 08:29:04 84410107 No FFTs found in tune.txt that can handle 84410107. Consider tuning with -tune
20261111 08:29:04 84410107 config:
20261111 08:29:04 84410107 FFT: 1.75M 4:256:14:256:101 (46.00 bpw)
20261111 08:29:04 84410107 LL loaded @ 0 : 0000000000000004
20261111 08:29:04 84410107 In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:644:24: warning: double precision constant requires cl_khr_fp64, casting to single precision
644 | F ay = a.y * (float) M_SQRT1_2;
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:645:30: warning: double precision constant requires cl_khr_fp64, casting to single precision
645 | return U2(fma(a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:645:64: warning: double precision constant requires cl_khr_fp64, casting to single precision
645 | return U2(fma(a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:652:24: warning: double precision constant requires cl_khr_fp64, casting to single precision
652 | F ay = a.y * (float) M_SQRT1_2;
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:653:31: warning: double precision constant requires cl_khr_fp64, casting to single precision
653 | return U2(fma(-a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, -ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:653:65: warning: double precision constant requires cl_khr_fp64, casting to single precision
653 | return U2(fma(-a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, -ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:63:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
63 | X2ad(u[0], u[1], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:64:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
64 | X2ad(u[2], u[3], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:246:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
246 | const float C1 = 0.92387953251128674, // cos(tau/16)
| ^
/tmp/openclon12/fft8.cl:247:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
247 | S1 = 0.38268343236508978, // sin(tau/16)
| ^
/tmp/openclon12/fft8.cl:248:28: warning: double precision constant requires cl_khr_fp64, casting to single precision
248 | S1_over_C1 = 0.4142135623730950488017,
| ^
/tmp/openclon12/fft8.cl:249:28: warning: double precision constant requires cl_khr_fp64, casting to single precision
249 | C1_over_S1 = 2.4142135623730950488017;
| ^
/tmp/openclon12/fft8.cl:259:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
259 | X2ad(u[0], u[2], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:267:22: warning: double precision constant requires cl_khr_fp64, casting to single precision
267 | X2t4ad(u[4], u[6], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1329:19: error: invalid output constraint '+v' in asm
1329 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1358:19: error: invalid output constraint '+v' in asm
1358 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1897:21: error: invalid output constraint '+v' in asm
1897 | if (HOIST >= 1) OPAQUE(me);
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1913:21: error: invalid output constraint '+v' in asm
1913 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1973:19: error: invalid output constraint '+v' in asm
1973 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1997:19: error: invalid output constraint '+v' in asm
1997 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2166:21: error: invalid output constraint '+v' in asm
2166 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2225:19: error: invalid output constraint '+v' in asm
2225 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2249:19: error: invalid output constraint '+v' in asm
2249 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2418:21: error: invalid output constraint '+v' in asm
2418 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:6:
/tmp/openclon12/weight.cl:135:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
135 | 0.090507732665257662,
| ^
/tmp/openclon12/weight.cl:136:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
136 | 0.18920711500272105,
| ^
/tmp/openclon12/weight.cl:137:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
137 | 0.29683955465100964,
| ^
/tmp/openclon12/weight.cl:138:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
138 | 0.41421356237309503,
| ^
/tmp/openclon12/weight.cl:139:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
139 | 0.54221082540794086,
| ^
/tmp/openclon12/weight.cl:140:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
140 | 0.68179283050742912,
| ^
/tmp/openclon12/weight.cl:141:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
141 | 0.83400808640934243,
| ^
/tmp/openclon12/weight.cl:150:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
150 | -0.082995956795328771,
| ^
/tmp/openclon12/weight.cl:151:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
151 | -0.15910358474628547,
| ^
/tmp/openclon12/weight.cl:152:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
152 | -0.2288945872960296,
| ^
/tmp/openclon12/weight.cl:153:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
153 | -0.29289321881345248,
| ^
/tmp/openclon12/weight.cl:154:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
154 | -0.35158022267449518,
| ^
/tmp/openclon12/weight.cl:155:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
155 | -0.40539644249863949,
| ^
/tmp/openclon12/weight.cl:156:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
156 | -0.45474613366737116,
| ^
/tmp/openclon12/weight.cl:214:41: warning: double precision constant requires cl_khr_fp64, casting to single precision
214 | *w1 = U2(optionalDouble(fancyMul(w.x, IWEIGHT_STEP), wrap1), optionalHalve(fancyMul(w.y, WEIGHT_STEP), wrap1));
| ^
<built-in>:418:23: note: expanded from macro 'IWEIGHT_STEP'
16 | #define IWEIGHT_STEP -9.8584036958340214e-05
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:6:
/tmp/openclon12/weight.cl:214:92: warning: double precision constant requires cl_khr_fp64, casting to single precision
214 | *w1 = U2(optionalDouble(fancyMul(w.x, IWEIGHT_STEP), wrap1), optionalHalve(fancyMul(w.y, WEIGHT_STEP), wrap1));
| ^
<built-in>:417:21: note: expanded from macro 'WEIGHT_STEP'
15 | #define WEIGHT_STEP 9.8593756728897436e-05
| ^
In file included from input.cl:1:
/tmp/openclon12/fftp.cl:605:39: warning: double precision constant requires cl_khr_fp64, casting to single precision
605 | F w2 = optionalHalve(fancyMul(w1, WEIGHT_STEP), frac_bits + FRAC_BPW_HI > FRAC_BPW_HI);
| ^
<built-in>:417:21: note: expanded from macro 'WEIGHT_STEP'
15 | #define WEIGHT_STEP 9.8593756728897436e-05
| ^
Error executing LLVM compilation action.
20261111 08:29:04 84410107 Compiling 'fftp.cl' error COMPILE_PROGRAM_FAILURE (-15) (args -cl-finite-math-only -cl-std=CL2.0 -DEXP=84410107uL -DWIDTH=256u -DSMALL_HEIGHT=256u -DMIDDLE=14u -DCARRY_LEN=8u -DNW=4u -DNH=4u -DAMDGPU=1 -DNO_FP64=1 -DCARRY64=1 -DCARRY_SUB_X=1 -DFFT_VARIANT=101u -DMAXBPW=5039u -DSTATS_SIZE=100000u -DWEIGHT_STEP=9.8593756728897436e-05 -DIWEIGHT_STEP=-9.8584036958340214e-05 -DTAILT=U2(-7.52981578e-05f,0.0122715384f) -DTRIG_SCALE=1.52587891e-05f -DTRIG_SIN={0.448798954f,-5.42732081e-09f,-0.0150662027f,0.000151708286f,-7.15217311e-07f,} -DTRIG_COS={1.00000000f,-0.100710250f,0.00169042510f,-1.13484766e-05f,4.02643643e-08f,} -DTAILTGF31=U2(509684486u,293249438u) -DTAILTGF61=U2(249938719029223731uL,1245372627562045535uL) -DPFA=7u -DPFA_LINV=2u -DPFA_BHINV=1u -DPFA_RINV31=9u -DPFA_W31=1205362885u -DPFA_RINV61=35u -DPFA_W61=1165310750493918737uL -DFFT_TYPE=4 -DWordSize=8u -DDISTGF31=573440u -DDISTWTRIGGF31=115392u -DDISTMTRIGGF31=1920u -DDISTHTRIGGF31=115392u -DDISTGF61=1146880uL -DDISTWTRIGGF61=230656uL -DDISTMTRIGGF61=3840uL -DDISTHTRIGGF61=230656uL -DFRAC_BPW_HI=4294356406u -DFRAC_BPW_LO=3681400538u -DNO_INT128=1 -DFFT_FP64=0 -DFFT_FP32=1 -DNTT_GF31=1 -DNTT_GF61=1 )
20261111 08:29:04 84410107 Can't compile fftp.cl
20261111 08:29:04 84410107 Can't build FFT 4:256:14:256:101 (Can't compile fftp.cl), trying the next untuned FFT
20261111 08:29:04 84410107 config:
20261111 08:29:04 84410107 Using CARRY64
20261111 08:29:04 84410107 FFT: 2.25M 1:256:9:512:101 (35.78 bpw)
20261111 08:29:04 84410107 LL loaded @ 0 : 0000000000000004
20261111 08:29:04 84410107 In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1973:19: error: invalid output constraint '+v' in asm
1973 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1997:19: error: invalid output constraint '+v' in asm
1997 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2166:21: error: invalid output constraint '+v' in asm
2166 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2225:19: error: invalid output constraint '+v' in asm
2225 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2249:19: error: invalid output constraint '+v' in asm
2249 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2418:21: error: invalid output constraint '+v' in asm
2418 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
Error executing LLVM compilation action.
20261111 08:29:04 84410107 Compiling 'fftp.cl' error COMPILE_PROGRAM_FAILURE (-15) (args -cl-finite-math-only -cl-std=CL2.0 -DEXP=84410107uL -DWIDTH=256u -DSMALL_HEIGHT=512u -DMIDDLE=9u -DCARRY_LEN=8u -DNW=4u -DNH=8u -DAMDGPU=1 -DNO_FP64=1 -DCARRY64=1 -DMUL3_CARRY64=1 -DFFT_VARIANT=101u -DMAXBPW=3963u -DSTATS_SIZE=100000u -DTAILTGF31=U2(269176336u,500380354u) -DTAILTGF61=U2(807738046998073027uL,30095103403839256uL) -DPFA=9u -DPFA_LINV=2u -DPFA_BHINV=8u -DPFA_RINV31=7u -DPFA_W31=309107220u -DPFA_RINV61=34u -DPFA_W61=1102844585000305877uL -DFFT_TYPE=1 -DWordSize=8u -DDISTGF31=0 -DDISTWTRIGGF31=0 -DDISTMTRIGGF31=0 -DDISTHTRIGGF31=0 -DDISTGF61=737280uL -DDISTWTRIGGF61=128uL -DDISTMTRIGGF61=2432uL -DDISTHTRIGGF61=74560uL -DFRAC_BPW_HI=3340054983u -DFRAC_BPW_LO=477218587u -DNO_INT128=1 -DFFT_FP64=0 -DFFT_FP32=0 -DNTT_GF31=1 -DNTT_GF61=1 )
20261111 08:29:04 84410107 Can't compile fftp.cl
20261111 08:29:04 84410107 Can't build FFT 1:256:9:512:101 (Can't compile fftp.cl), trying the next untuned FFT
20261111 08:29:04 84410107 config:
20261111 08:29:04 84410107 Using CARRY64
20261111 08:29:04 84410107 FFT: 2.50M 2:1K:5:256:101 (32.20 bpw)
20261111 08:29:04 84410107 LL loaded @ 0 : 0000000000000004
20261111 08:29:04 84410107 In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:644:24: warning: double precision constant requires cl_khr_fp64, casting to single precision
644 | F ay = a.y * (float) M_SQRT1_2;
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:645:30: warning: double precision constant requires cl_khr_fp64, casting to single precision
645 | return U2(fma(a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:645:64: warning: double precision constant requires cl_khr_fp64, casting to single precision
645 | return U2(fma(a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:652:24: warning: double precision constant requires cl_khr_fp64, casting to single precision
652 | F ay = a.y * (float) M_SQRT1_2;
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:653:31: warning: double precision constant requires cl_khr_fp64, casting to single precision
653 | return U2(fma(-a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, -ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:18:
/tmp/openclon12/math.cl:653:65: warning: double precision constant requires cl_khr_fp64, casting to single precision
653 | return U2(fma(-a.x, (float) M_SQRT1_2, -ay), fma(a.x, (float) M_SQRT1_2, -ay));
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:63:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
63 | X2ad(u[0], u[1], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:64:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
64 | X2ad(u[2], u[3], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:246:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
246 | const float C1 = 0.92387953251128674, // cos(tau/16)
| ^
/tmp/openclon12/fft8.cl:247:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
247 | S1 = 0.38268343236508978, // sin(tau/16)
| ^
/tmp/openclon12/fft8.cl:248:28: warning: double precision constant requires cl_khr_fp64, casting to single precision
248 | S1_over_C1 = 0.4142135623730950488017,
| ^
/tmp/openclon12/fft8.cl:249:28: warning: double precision constant requires cl_khr_fp64, casting to single precision
249 | C1_over_S1 = 2.4142135623730950488017;
| ^
/tmp/openclon12/fft8.cl:259:20: warning: double precision constant requires cl_khr_fp64, casting to single precision
259 | X2ad(u[0], u[2], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
In file included from /tmp/openclon12/fftbase.cl:5:
/tmp/openclon12/fft8.cl:267:22: warning: double precision constant requires cl_khr_fp64, casting to single precision
267 | X2t4ad(u[4], u[6], M_SQRT1_2);
| ^
/usr/lib/clang/23/include/opencl-c-base.h:238:23: note: expanded from macro 'M_SQRT1_2'
238 | #define M_SQRT1_2 0x1.6a09e667f3bcdp-1
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1329:19: error: invalid output constraint '+v' in asm
1329 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1358:19: error: invalid output constraint '+v' in asm
1358 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1857:19: error: invalid output constraint '+v' in asm
1857 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:1863:19: error: invalid output constraint '+v' in asm
1863 | if (HOIST >= 1) OPAQUE(me);
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2225:19: error: invalid output constraint '+v' in asm
2225 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2249:19: error: invalid output constraint '+v' in asm
2249 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2376:19: error: invalid output constraint '+v' in asm
2376 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2382:19: error: invalid output constraint '+v' in asm
2382 | if (HOIST >= 1) OPAQUE(me);
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:6:
/tmp/openclon12/weight.cl:135:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
135 | 0.090507732665257662,
| ^
/tmp/openclon12/weight.cl:136:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
136 | 0.18920711500272105,
| ^
/tmp/openclon12/weight.cl:137:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
137 | 0.29683955465100964,
| ^
/tmp/openclon12/weight.cl:138:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
138 | 0.41421356237309503,
| ^
/tmp/openclon12/weight.cl:139:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
139 | 0.54221082540794086,
| ^
/tmp/openclon12/weight.cl:140:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
140 | 0.68179283050742912,
| ^
/tmp/openclon12/weight.cl:141:5: warning: double precision constant requires cl_khr_fp64, casting to single precision
141 | 0.83400808640934243,
| ^
/tmp/openclon12/weight.cl:150:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
150 | -0.082995956795328771,
| ^
/tmp/openclon12/weight.cl:151:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
151 | -0.15910358474628547,
| ^
/tmp/openclon12/weight.cl:152:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
152 | -0.2288945872960296,
| ^
/tmp/openclon12/weight.cl:153:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
153 | -0.29289321881345248,
| ^
/tmp/openclon12/weight.cl:154:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
154 | -0.35158022267449518,
| ^
/tmp/openclon12/weight.cl:155:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
155 | -0.40539644249863949,
| ^
/tmp/openclon12/weight.cl:156:6: warning: double precision constant requires cl_khr_fp64, casting to single precision
156 | -0.45474613366737116,
| ^
/tmp/openclon12/weight.cl:214:41: warning: double precision constant requires cl_khr_fp64, casting to single precision
214 | *w1 = U2(optionalDouble(fancyMul(w.x, IWEIGHT_STEP), wrap1), optionalHalve(fancyMul(w.y, WEIGHT_STEP), wrap1));
| ^
<built-in>:418:23: note: expanded from macro 'IWEIGHT_STEP'
16 | #define IWEIGHT_STEP -0.42569045824999574
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:6:
/tmp/openclon12/weight.cl:214:92: warning: double precision constant requires cl_khr_fp64, casting to single precision
214 | *w1 = U2(optionalDouble(fancyMul(w.x, IWEIGHT_STEP), wrap1), optionalHalve(fancyMul(w.y, WEIGHT_STEP), wrap1));
| ^
<built-in>:417:21: note: expanded from macro 'WEIGHT_STEP'
15 | #define WEIGHT_STEP 0.74122128800586407
| ^
In file included from input.cl:1:
/tmp/openclon12/fftp.cl:420:39: warning: double precision constant requires cl_khr_fp64, casting to single precision
420 | F w2 = optionalHalve(fancyMul(w1, WEIGHT_STEP), frac_bits + FRAC_BPW_HI > FRAC_BPW_HI);
| ^
<built-in>:417:21: note: expanded from macro 'WEIGHT_STEP'
15 | #define WEIGHT_STEP 0.74122128800586407
| ^
Error executing LLVM compilation action.
20261111 08:29:04 84410107 Compiling 'fftp.cl' error COMPILE_PROGRAM_FAILURE (-15) (args -cl-finite-math-only -cl-std=CL2.0 -DEXP=84410107uL -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=5u -DCARRY_LEN=8u -DNW=8u -DNH=4u -DAMDGPU=1 -DNO_FP64=1 -DCARRY64=1 -DMUL3_CARRY64=1 -DFFT_VARIANT=101u -DMAXBPW=3462u -DSTATS_SIZE=100000u -DWEIGHT_STEP=0.74122128800586407 -DIWEIGHT_STEP=-0.42569045824999574 -DTAILT=U2(-7.52981578e-05f,0.0122715384f) -DTRIG_SCALE=7.62939453e-06f -DTRIG_SIN={0.628318548f,-1.95191774e-08f,-0.0413416624f,0.000815923559f,-7.53935637e-06f,} -DTRIG_COS={1.00000000f,-0.197392091f,0.00649393676f,-8.54487662e-05f,5.94217113e-07f,} -DTAILTGF61=U2(249938719029223731uL,1245372627562045535uL) -DPFA=5u -DPFA_LINV=4u -DPFA_BHINV=1u -DPFA_RINV61=49u -DPFA_W61=725554454131936870uL -DFFT_TYPE=2 -DWordSize=8u -DDISTGF61=819200uL -DDISTWTRIGGF61=2560uL -DDISTMTRIGGF61=1152uL -DDISTHTRIGGF61=164544uL -DFRAC_BPW_HI=858565836u -DFRAC_BPW_LO=3435973835u -DNO_INT128=1 -DFFT_FP64=0 -DFFT_FP32=1 -DNTT_GF31=0 -DNTT_GF61=1 )
20261111 08:29:04 84410107 Can't compile fftp.cl
20261111 08:29:04 84410107 Can't build FFT 2:1K:5:256:101 (Can't compile fftp.cl), trying the next untuned FFT
20261111 08:29:04 84410107 config:
20261111 08:29:04 84410107 Using CARRY64
20261111 08:29:05 84410107 FFT: 3.50M 3:1K:7:256:101 (23.00 bpw)
20261111 08:29:05 84410107 LL loaded @ 0 : 0000000000000004
20261111 08:29:05 84410107 In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2225:19: error: invalid output constraint '+v' in asm
2225 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2249:19: error: invalid output constraint '+v' in asm
2249 | if (HOIST == 2) OPAQUE(me); // Twiddle loads not issued before the butterflies preceding this call (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2376:19: error: invalid output constraint '+v' in asm
2376 | if (HOIST >= 1) OPAQUE(me); // This step's LDS addresses and twiddle loads are not computed before the step starts (see HOIST_W/H)
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
In file included from input.cl:1:
In file included from /tmp/openclon12/fftp.cl:5:
In file included from /tmp/openclon12/fftwidth.cl:20:
/tmp/openclon12/fftbase.cl:2382:19: error: invalid output constraint '+v' in asm
2382 | if (HOIST >= 1) OPAQUE(me);
| ^
/tmp/openclon12/base.cl:1094:39: note: expanded from macro 'OPAQUE'
1094 | #define OPAQUE(x) __asm volatile("" : "+v"(x))
| ^
Error executing LLVM compilation action.
20261111 08:29:05 84410107 Compiling 'fftp.cl' error COMPILE_PROGRAM_FAILURE (-15) (args -cl-finite-math-only -cl-std=CL2.0 -DEXP=84410107uL -DWIDTH=1024u -DSMALL_HEIGHT=256u -DMIDDLE=7u -DCARRY_LEN=8u -DNW=8u -DNH=4u -DAMDGPU=1 -DNO_FP64=1 -DCARRY64=1 -DMUL3_CARRY64=1 -DFFT_VARIANT=101u -DMAXBPW=2389u -DSTATS_SIZE=100000u -DTAILTGF61=U2(249938719029223731uL,1245372627562045535uL) -DPFA=7u -DPFA_LINV=1u -DPFA_BHINV=2u -DPFA_RINV61=35u -DPFA_W61=1165310750493918737uL -DFFT_TYPE=3 -DWordSize=4u -DDISTGF61=0 -DDISTWTRIGGF61=0 -DDISTMTRIGGF61=0 -DDISTHTRIGGF61=0 -DFRAC_BPW_HI=4294661851u -DFRAC_BPW_LO=1840700268u -DNO_INT128=1 -DFFT_FP64=0 -DFFT_FP32=0 -DNTT_GF31=0 -DNTT_GF61=1 )
20261111 08:29:05 84410107 Can't compile fftp.cl
20261111 08:29:05 Exception "Can't compile fftp.cl"
20261111 08:29:05 Bye
2026-11-11 08:29:05 (1395833): ./prpll exited; CPU time 1.114378
2026-11-11 08:29:05 (1395833): app exit status: 0x1
2026-11-11 08:29:05 (1395833): called boinc_finish(195)
</stderr_txt>
]]>
Main page · Your account · Message boards
Copyright © 2014-2026 BOINC Confederation / rebirther