appujee
appujee
``` + clang -c -Iexternal/bcc/libbpf-tools/x86 -Iexternal/bcc/libbpf-tools -m32 -march=prescott --target=bpf -fno-data-sections -fno-function-sections -fno-stack-protector -fno-unwind-tables -mcpu=generic -Wno-pointer-arith -Wno-unused-command-line-argument -Wno-unused-parameter -fno-addrsig -D__TARGET_ARCH_x86 -Iexternal/bcc/libbpf-tools/x86 -Iexternal/bcc/libbpf-tools -D__LIBC_API__=10000 -D__LIBM_API__=10000 -D__LIBDL_API__=10000 -Isystem/bpf/progs/include -Iexternal/libcxxabi/include -Iexternal/libcxx/include -Ibionic/libc/async_safe/include -Isystem/logging/liblog/include -Ibionic/libc/system_properties/include...
``` PASS: env -i uses old $PATH FAIL: env -i env echo -ne '' | "/system/bin/env" -i env --- expected 2023-03-06 18:22:13.948004125 +0000 +++ actual 2023-03-06 18:22:13.968004126 +0000 @@ -0,0...
Maybe we can add this to clang driver once we have tested it?
Android support ABIs are documented in https://developer.android.com/ndk/guides/abis. It needs to mention RISC-V too. - [ ] [#102] - [ ] [#103] - [ ] [#101]
bloaty can be used to analyze the binary - [ ] Binary size of different sections - [ ] Number of rebases and fixups Check instructions that shouldn't be in...
get this to land: https://reviews.llvm.org/D134129
- [x] Compiling [TSVC](https://github.com/UoB-HPC/TSVC_2) benchmark would be a good way to find out if commonly found loop structures are getting vectorized. - [ ] Instruction scheduling of vectorized loops. If...
As per [Super-Node SLP: Optimized Vectorization for Code Sequences Containing Operators and Their Inverse Elements](https://rcor.me/papers/cgo19snslp.pdf) the following benchmarks may have interesting code for SLP vectorization opportunities - 433.milc - 453.povray...
At least the important ones when building aosp: - [ ] number of spills - [ ] number of functions inlined