Hi, @BoonBengT_Intel :
I am sorry to bother you, I had posted my problems above and solved part of them by myself. BUT I think I need to reorganize those problems here to make it a clear read.
If you could help me to solve and understand the remaining problems, I would be good!
The sample is about QR decomposition in DPC++FPGA.
First, I submitted the following node to compile for FPGA emulation successful.
qsub -I -l nodes=1:fpga_compile:ppn=2 -d .
make fpga_emu
and here is the result, but I don't know why there are so many warnings. (?)
-- Configuring the design to run on FPGA board intel_s10sx_pac:pac_s10
-- ROWS_COMPONENT=256
-- COLS_COMPONENT=256
-- FIXED_ITERATIONS=105
-- SEED=5
-- Configuring done
-- Generating done
-- Build files have been written to: /home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/build
Scanning dependencies of target qrd.fpga_emu
[ 33%] Building CXX object src/CMakeFiles/qrd.fpga_emu.dir/qrd_demo.cpp.o
/home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/src/qrd_demo.cpp:192:15: warning: comparison with NaN always evaluates to false in fast floating point modes [-Wtautological-constant-compare]
if (std::isnan(v_matrix[row][col][0]) ||
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/src/qrd_demo.cpp:193:15: warning: comparison with NaN always evaluates to false in fast floating point modes [-Wtautological-constant-compare]
std::isnan(v_matrix[row][col][1])) {
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2 warnings generated.
/home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/src/qrd_demo.cpp:192:15: warning: comparison with NaN always evaluates to false in fast floating point modes [-Wtautological-constant-compare]
if (std::isnan(v_matrix[row][col][0]) ||
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/src/qrd_demo.cpp:193:15: warning: comparison with NaN always evaluates to false in fast floating point modes [-Wtautological-constant-compare]
std::isnan(v_matrix[row][col][1])) {
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
2 warnings generated.
[ 66%] Building CXX object src/CMakeFiles/qrd.fpga_emu.dir/qrd.cpp.o
[100%] Linking CXX executable ../qrd.fpga_emu
Platform name: Intel(R) FPGA Emulation Platform for OpenCL(TM)
Device name: Intel(R) FPGA Emulation Device
Driver version: 2021.12.9.0.24_005321
OpenCL program was successfully created from SPIR-V file /home/u77513/tmp/qrd_demo-3c97b6-63c7cf.spv
Using build options: -g -I "/home/u77513/tmp"
build log:
Compilation started
Compilation done
Linking started
Linking done
Device build started
Options used by backend compiler: -g -I "/home/u77513/tmp"
Device build done
Kernel <_ZTS3QRD> was successfully vectorized (16)
Done.
OpenCL program binary file was successfully created: /home/u77513/tmp/qrd_demo-f12b0d-bbc0b9.aocx
[100%] Built target qrd.fpga_emu
Scanning dependencies of target fpga_emu
[100%] Built target fpga_emu
Then, I want to compile for FPGA hardware also using the following command.
qsub -I -l nodes=1:fpga_compile:ppn=2 -d .
make fpga
But the errors happened, as following. Maybe the reason is not every node in devcloud have FPGA hardware ?
Scanning dependencies of target qrd.fpga
[ 33%] Building CXX object src/CMakeFiles/qrd.fpga.dir/qrd_demo.cpp.o
[ 66%] Building CXX object src/CMakeFiles/qrd.fpga.dir/qrd.cpp.o
[100%] Linking CXX executable ../qrd.fpga
Warning: Command has been deprecated. Please use -ffp-reassociate instead of -fp-relaxed
warning: -reuse-exe file '/home/u77513/oneAPI-samples/DirectProgramming/DPC++FPGA/ReferenceDesigns/qrd/build/qrd.fpga' not found; ignored
aoc: Compiling for FPGA. This process may take several hours to complete. Prior to performing this compile, be sure to check the reports to ensure the design will meet your performance targets. If the reports indicate performance targets are not being met, code edits may be required. Please refer to the oneAPI FPGA Optimization Guide for information on performance tuning applications for FPGAs.
Error (23035): Tcl error:
Error (23031): Evaluation of Tcl script build/entry.tcl unsuccessful
Error: Quartus Prime Shell was unsuccessful. 2 errors, 0 warnings
For more details, full Quartus compile output can be found in files quartuserr.tmp and quartus_sh_compile.log.
Error: Compiler Error, not able to generate hardware
llvm-foreach:
dpcpp: error: fpga compiler command failed with exit code 1 (use -v to see invocation)
make[3]: *** [src/CMakeFiles/qrd.fpga.dir/build.make:99: qrd.fpga] Error 1
make[2]: *** [CMakeFiles/Makefile2:100: src/CMakeFiles/qrd.fpga.dir/all] Error 2
make[1]: *** [CMakeFiles/Makefile2:215: src/CMakeFiles/fpga.dir/rule] Error 2
make: *** [Makefile:170: fpga] Error 2
I really look forward to your reply! Thanks so much!
