doc update and better error

Author: ZuseZ4

compiler/rustc_codegen_llvm/src/back/write.rs

@@ -799,12 +799,18 @@ pub(crate) unsafe fn llvm_optimize(
             let device_pathbuf = PathBuf::from(device_path);
             if device_pathbuf.is_relative() {
                 panic!("Absolute path is needed");
+            } else if device_pathbuf
+                .file_name()
+                .and_then(|n| n.to_str())
+                .is_some_and(|n| n != "host.out")
+            {
+                panic!("Need path to the host.out file");
             }
             assert!(device_pathbuf.exists());
             let host_dir = device_pathbuf.parent().unwrap();
-            let host_out = host_dir.join("host.out");
+            //let host_out = host_dir.join("host.out");
             let out_obj = host_dir.join("host.o");
-            let host_out_c = path_to_c_string(host_out.as_path());
+            let host_out_c = path_to_c_string(device_pathbuf.as_path());
 
             // 2) Finalize host: lib.bc + host.out -> host.offload.o (host TM created in C++)
             let llmod2 = llvm::LLVMCloneModule(module.module_llvm.llmod());

src/doc/rustc-dev-guide/src/offload/usage.md

@@ -77,25 +77,25 @@ pub extern "gpu-kernel" fn kernel_1(x: *mut [f64; 256]) {
 ## Compile instructions
 It is important to use a clang compiler build on the same llvm as rustc. Just calling clang without the full path will likely use your system clang, which probably will be incompatible. So either substitute clang/lld invocations below with absolute path, or set your `PATH` accordingly.
 
-First we generate the host (cpu) code.
+First we generate the device (gpu) code. Replace the target-cpu with the right code for your gpu.
 ```
-RUSTFLAGS="--emit=llvm-bc -Zoffload=Enable -Zunstable-options" cargo +offload build -r 
+RUSTFLAGS="-Ctarget-cpu=gfx90a --emit=llvm-bc,llvm-ir -Zoffload=Device -Csave-temps -Zunstable-options" cargo +offload build -Zunstable-options -r -v --target amdgcn-amd-amdhsa -Zbuild-std=core
 ```
 You might afterwards need to copy your target/release/deps/<lib_name>.bc to lib.bc for now, before the next step.
 
-Now we generate the device code. Replace the target-cpu with the right code for your gpu.
+Now we generate the host (cpu) code.
 ```
-RUSTFLAGS="-Ctarget-cpu=gfx90a -Zoffload=Enable -Zunstable-options" cargo +offload build -Zunstable-options -r --target amdgcn-amd-amdhsa -Zbuild-std=core
+RUSTFLAGS="--emit=llvm-bc,llvm-ir -Csave-temps -Zoffload=Host=/p/lustre1/drehwald1/prog/offload/r/target/amdgcn-amd-amdhsa/release/deps/host.out -Zunstable-options" cargo +offload build -r
 ```
 This call also does a lot of work and generates multiple intermediate files for llvm offload.
 While we integrated most offload steps into rustc by now, one binary invocation still remains for now:
 
 ```
-"clang-linker-wrapper" "--should-extract=gfx90a" "--device-compiler=amdgcn-amd-amdhsa=-g" "--device-compiler=amdgcn-amd-amdhsa=-save-temps=cwd" "--device-linker=amdgcn-amd-amdhsa=-lompdevice" "--host-triple=x86_64-unknown-linux-gnu" "--save-temps" "--linker-path=/ABSOlUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/lld/bin/ld.lld" "--hash-style=gnu" "--eh-frame-hdr" "-m" "elf_x86_64" "-pie" "-dynamic-linker" "/lib64/ld-linux-x86-64.so.2" "-o" "bare" "/lib/../lib64/Scrt1.o" "/lib/../lib64/crti.o" "/ABSOLUTE_PATH_TO/crtbeginS.o" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/bin/../lib/x86_64-unknown-linux-gnu" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/lib/clang/21/lib/x86_64-unknown-linux-gnu" "-L/lib/../lib64" "-L/usr/lib64" "-L/lib" "-L/usr/lib" "host.o" "-lstdc++" "-lm" "-lomp" "-lomptarget" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/lib" "-lgcc_s" "-lgcc" "-lpthread" "-lc" "-lgcc_s" "-lgcc" "/ABSOLUTE_PATH_TO/crtendS.o" "/lib/../lib64/crtn.o"
+"clang-linker-wrapper" "--should-extract=gfx90a" "--device-compiler=amdgcn-amd-amdhsa=-g" "--device-compiler=amdgcn-amd-amdhsa=-save-temps=cwd" "--device-linker=amdgcn-amd-amdhsa=-lompdevice" "--host-triple=x86_64-unknown-linux-gnu" "--save-temps" "--linker-path=/ABSOlUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/lld/bin/ld.lld" "--hash-style=gnu" "--eh-frame-hdr" "-m" "elf_x86_64" "-pie" "-dynamic-linker" "/lib64/ld-linux-x86-64.so.2" "-o" "bare" "/lib/../lib64/Scrt1.o" "/lib/../lib64/crti.o" "/ABSOLUTE_PATH_TO/crtbeginS.o" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/bin/../lib/x86_64-unknown-linux-gnu" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/lib/clang/21/lib/x86_64-unknown-linux-gnu" "-L/lib/../lib64" "-L/usr/lib64" "-L/lib" "-L/usr/lib" "target/<GPU_DIR>/release/host.o" "-lstdc++" "-lm" "-lomp" "-lomptarget" "-L/ABSOLUTE_PATH_TO/rust/build/x86_64-unknown-linux-gnu/llvm/lib" "-lgcc_s" "-lgcc" "-lpthread" "-lc" "-lgcc_s" "-lgcc" "/ABSOLUTE_PATH_TO/crtendS.o" "/lib/../lib64/crtn.o"
 ```
 
 You can try to find the paths to those files on your system. However, I recommend to not fix the paths, but rather just re-generate them by copying a bare-mode openmp example and compiling it with your clang. By adding `-###` to your clang invocation, you can see the invidual steps.
-It will show multiple steps, just look for the clang-linker-wrapper example. Make sure to still include the `host.o` file, and not whatever tmp file you got when compiling your c++ example with the following call.
+It will show multiple steps, just look for the clang-linker-wrapper example. Make sure to still include the path to the `host.o` file, and not whatever tmp file you got when compiling your c++ example with the following call.
 ```
 myclang++ -fuse-ld=lld -O3 -fopenmp  -fopenmp-offload-mandatory --offload-arch=gfx90a omp_bare.cpp -o main -###
 ```