pytorch - 💡(How to fix) Fix C++ compile error when indirect indexing a transposed tensor: transpose_mxn references a tmp variable defined inside of the loop [1 comments, 1 participants]

import torch


def f(buf, idx):
    return buf[torch.arange(buf.shape[0]), idx, :]

buf = torch.randn(16, 2, 16).permute(2, 1, 0)
idx = torch.randint(0, 2, (16,))

torch.compile(f, backend="inductor")(buf, idx)

---

#include <torch/csrc/inductor/cpp_prefix.h>
extern "C"  void  kernel(const int64_t* in_ptr0,
                       const float* in_ptr1,
                       float* out_ptr0)
{
    {
        for(int64_t x0=static_cast<int64_t>(0L); x0<static_cast<int64_t>(16L); x0+=static_cast<int64_t>(16L))
        {
            for(int64_t x1=static_cast<int64_t>(0L); x1<static_cast<int64_t>(16L); x1+=static_cast<int64_t>(16L))
            {
                {
                    if(C10_LIKELY(x0 >= static_cast<int64_t>(0) && x0 < static_cast<int64_t>(16L) && x1 >= static_cast<int64_t>(0) && x1 < static_cast<int64_t>(16L)))
                    {
                        alignas(std::max(std::size_t(16), alignof(float))) float tmp9[16*16];
                        transpose_mxn<float,static_cast<int64_t>(16),static_cast<int64_t>(16),false>(in_ptr1 + static_cast<int64_t>(x0 + 16L*tmp5 + 32L*x1), static_cast<int64_t>(32L), tmp9, static_cast<int64_t>(16));
                        for (long x0_inner = 0; x0_inner < static_cast<int64_t>(16); x0_inner++)
                        {
                            auto tmp0 = in_ptr0[static_cast<int64_t>(x0 + x0_inner)];
                            auto tmp1 = 2L;
                            auto tmp2 = c10::convert<int64_t>(tmp1);
                            auto tmp3 = int64_t(tmp0 + tmp2);
                            auto tmp4 = tmp0 < 0;
                            auto tmp5 = tmp4 ? tmp3 : tmp0;
                            auto tmp6 = tmp5;
                            auto tmp7 = c10::convert<int64_t>(tmp6);
                            TORCH_CHECK((0 <= tmp7) & (tmp7 < 2L), "index out of bounds: 0 <= tmp7 < 2L");
                            auto tmp10 = at::vec::Vectorized<float>::loadu(tmp9 + static_cast<int64_t>(16L*x0_inner), static_cast<int64_t>(16));
                            tmp10.store(out_ptr0 + static_cast<int64_t>(x1 + 16L*x0 + 16L*x0_inner));
                        }
                    }
                }
            }
        }
    }
}
// ... python bindings are omitted

---

torch._inductor.exc.InductorError: CppCompileError: C++ compile error

Command:
g++ /tmp/torchinductor_vscode/kc/ckcky6bnqwfoc7y6s4lk7fjtolr6dphcgenbfk36hlhkitkzh524.main.cpp -D TORCH_INDUCTOR_CPP_WRAPPER -D STANDALONE_TORCH_HEADER -D TORCH_INDUCTOR_PRECOMPILE_HEADERS -D C10_USING_CUSTOM_GENERATED_MACROS -D CPU_CAPABILITY_AVX512 -O3 -DNDEBUG -fno-trapping-math -funsafe-math-optimizations -ffinite-math-only -fno-signed-zeros -fno-math-errno -fno-finite-math-only -fno-unsafe-math-optimizations -ffp-contract=off -fexcess-precision=fast -fno-tree-loop-vectorize -march=native -shared -fPIC -Wall -std=c++20 -Wno-unused-variable -Wno-unknown-pragmas -pedantic -fopenmp -include /tmp/torchinductor_vscode/precompiled_headers/c3xvd7kstka6ykzeisqbnzxvjp6d2bfdoavpupkltqxvdeilk763.h -I/usr/include/python3.12 -I/workspaces/av/reproducer/venv-nightly/lib/python3.12/site-packages/torch/include -I/workspaces/av/reproducer/venv-nightly/lib/python3.12/site-packages/torch/include/torch/csrc/api/include -mavx512f -mavx512dq -mavx512vl -mavx512bw -mfma -mavx512vnni -mavx512vl -o /tmp/torchinductor_vscode/kc/ckcky6bnqwfoc7y6s4lk7fjtolr6dphcgenbfk36hlhkitkzh524.main.so -ltorch -ltorch_cpu -ltorch_python -lgomp -L/usr/lib/x86_64-linux-gnu -L/workspaces/av/reproducer/venv-nightly/lib/python3.12/site-packages/torch/lib

Output:
/tmp/torchinductor_vscode/kc/ckcky6bnqwfoc7y6s4lk7fjtolr6dphcgenbfk36hlhkitkzh524.main.cpp: In function ‘void kernel(const int64_t*, const float*, float*)’:
/tmp/torchinductor_vscode/kc/ckcky6bnqwfoc7y6s4lk7fjtolr6dphcgenbfk36hlhkitkzh524.main.cpp:16:142: error: ‘tmp5’ was not declared in this scope; did you mean ‘tmp9’?
   16 |                         transpose_mxn<float,static_cast<int64_t>(16),static_cast<int64_t>(16),false>(in_ptr1 + static_cast<int64_t>(x0 + 16L*tmp5 + 32L*x1), static_cast<int64_t>(32L), tmp9, static_cast<int64_t>(16));
      |                                                                                                                                              ^~~~
      |                                                                                                                                              tmp9

---

Collecting environment information...
PyTorch version: 2.12.0.dev20260326+cpu
Is debug build: False
CUDA used to build PyTorch: Could not collect
ROCM used to build PyTorch: N/A

OS: Ubuntu 24.04.4 LTS (x86_64)
GCC version: (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.39

Python version: 3.12.3 (main, Mar  3 2026, 12:15:18) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-94-generic-x86_64-with-glibc2.39
Is CUDA available: False
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: GPU 0: NVIDIA RTX PRO 6000 Blackwell Server Edition
Nvidia driver version: 580.105.08
cuDNN version: Could not collect
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
Caching allocator config: N/A

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        52 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               128
On-line CPU(s) list:                  0-127
Vendor ID:                            AuthenticAMD
Model name:                           AMD EPYC 9355 32-Core Processor
CPU family:                           26
Model:                                2
Thread(s) per core:                   2
Core(s) per socket:                   32
Socket(s):                            2
Stepping:                             1
Frequency boost:                      enabled
CPU(s) scaling MHz:                   108%
CPU max MHz:                          3550.0000
CPU min MHz:                          1500.0000
BogoMIPS:                             7099.78
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx_vnni avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect movdiri movdir64b overflow_recov succor smca fsrm avx512_vp2intersect flush_l1d debug_swap
Virtualization:                       AMD-V
L1d cache:                            3 MiB (64 instances)
L1i cache:                            2 MiB (64 instances)
L2 cache:                             64 MiB (64 instances)
L3 cache:                             512 MiB (16 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0-31,64-95
NUMA node1 CPU(s):                    32-63,96-127
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected
Vulnerability Vmscape:                Not affected

Versions of relevant libraries:
[pip3] numpy==2.4.3
[pip3] torch==2.12.0.dev20260326+cpu
[pip3] torchvision==0.26.0.dev20260326+cpu
[conda] Could not collect