tree 9cfd36ea3fd903f7f382327788db8a7e74eccb7e
parent 0a03b4e8cb93c0a2e59896b5ab9b4d6be228f20a
author Zmicier Prybysh <zprybysh@baylibre.com> 1788515640 +0200
committer GitHub <noreply@github.com> 1788515640 +0000
gpgsig -----BEGIN PGP SIGNATURE-----
 
 wsFcBAABCAAQBQJqmpU4CRC1aQ7uu5UhlAAANvcQAHy3dAtqMAprbi50rsV/XuqB
 3RONAYNkqiSlC3myc8pgCCGsnqWVLdJKi4BuWgXLAcYEE55NX7iOkQRl/BMADrpI
 /YHdhYpHUTslbHWoCmpYXlT/zBwxG2BBiYk5z4YWMzOxX4S54phG6B7bg/tO8hp8
 n4XjdH3C9DLfdEb96+WItDIM+O+rIw7xnyNmPeaHYEptLQV/cHQhLVvDEn7ivN7n
 QjQrWCvCvnaJXcrMpQ2ArvN9xSCfmhuL88cBceQAIrtPgsKNTcmyw+75RUjMA4F1
 x0xIrk5E3PK8H7XslsGLdznadx1e543Mepdl19/JfyDAS3odJmOgGNiETr9B+d6m
 +Nu/j5bxFx158Os7yMvpuqhhjSBxRtYb3c37I0irWZh/dHsu7qhaOiYkIgMB0Utb
 6Cg1kzbewsI6jriIzVf8gyzARbl9mQvGDp3YbuQJwBPLNeWYK057s8DKfsYl9QuY
 JdRB5ORJGJ4veIhZVm464KiIB/4k4v1ZPhcZS56kVP8fr43YCofM3UMmK2qwXDuM
 BFSN3RrzVdKcTInrhBVRbmhZo2oQmfyRX4ByupdvO7F6mVBZnPXAH/CAc5dT2/ll
 EgGFzE0ptql6NW6mFxFj2/rOGnXtJ/fd0m4PsmlmCs4HdjUg4EIyeHKCywRoPDhL
 MKgHhZQAda3kTjwftmc4
 =+G1X
 -----END PGP SIGNATURE-----
 

[Codegen] Use overflow-checked math in the CPU and GPU alloc size checks (#24745)

`checkStackAllocationSize` accumulates the allocation size in a plain
int64_t. Allocas sized by the upper bound of an unbounded dynamic
dimension (the util.assume.int default, 2^53-1) overflow it, the wrapped
value passes the limit check and the alloca reaches ConvertToLLVM, where
its element count folds to llvm.mlir.poison and the program loads and
stores through a garbage pointer at runtime.

The reproduction was reduced from the quantized ResNet downsample
construct: an ONNX model with a dynamic batch doing DequantizeLinear ->
1x1 stride-2 Conv compiles without diagnostics and returns completely
wrong results.

Move `getStaticShapeSizeInBits` to Codegen/Utils (taken from
https://github.com/iree-org/iree/pull/24684) and use it from both
LLVMCPUCheckIRBeforeLLVMConversion and GPUCheckResourceUsage. Callers
supply the leaf element bit width,
which lets the GPU check keep its index-bitwidth handling and the
recursion into shaped element types. On the CPU side the remaining
scalar steps are overflow-checked in place with `llvm::MulOverflow` /
`llvm::AddOverflow`. The pre-existing
`checkedAdd`/`checkedMul`/`checkedAlignTo` wrappers in
LLVMCPUAssignWorkgroupLocalMemory.cpp are replaced with
`llvm::MulOverflow` / `llvm::AddOverflow`.

---------

Signed-off-by: Zmicier Prybysh <zprybysh@baylibre.com>