…ng#4275)

…ng#4323)

…ng#4374)

Update LLVM version to
llvm/llvm-project@dd7d81e

…ng#4410)

Included the use of the non-deprecated version of createMCObjectStreamer (needed after llvm/llvm-project@f1422a8).

…ng#4468)

…ng#4536)

…ich exists in gcc-defaults. (triton-lang#4548)

The llvm build check is trying to get
http://ftp.de.debian.org/debian/pool/main/g/gcc-defaults/gcc-aarch64-linux-gnu_13.2.0-7_amd64.deb,
which does not exist and therefore fails. Updating the version to an
existing one (14.1.0-2).

[x] I am not making a trivial change, such as fixing a typo in a
comment.
[x] I have written a PR description following these
  [rules](https://cbea.ms/git-commit/#why-not-how).
[x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`.
[x] This PR does not need a test because it is not a functional change,
should fix git checks builds.
[x] I have not added any `lit` tests.

Part of https://github.com/triton-lang/triton/pull/4548/files

…ng#4578)

The origin issue is reported here: triton-lang#3435
The issue happens during compilation, when arith.sitofp (from i8 to fp16) operates on the tensor operand which has dot_op layout with the first dimension of the tensor being 16 and opidx = 1.
For example: %104 = arith.sitofp %103 : tensor<16x64xi8, #triton_gpu.dot_op<{opIdx = 1, parent = #mma, kWidth = 4}>> to tensor<16x64xf16, #triton_gpu.dot_op<{opIdx = 1, parent = #mma, kWidth = 4}>>

Investigation shows that the bug happens in TritonGPUToLLVM pass.
in the corner case (block_k = 16 and opidx = 1) extra elements will be unpacked in include/triton/Conversion/TritonGPUToLLVM/ElementwiseOpToLLVM.h:line 186-194.
The code unpack extra elements due to an implicit assumption in lib/Dialect/TritonGPU/IR/Dialect.h, at line 2000, at least 4 rep will be loaded.

Therefore, in our patch, extra loaded elements are dropped in the corner case.