The current `DIScopeForLLVMFuncOp` pass handles debug information for
inlined code by processing `CallSiteLoc` attributes. However, some
compilation scenarios compose code from multiple source files directly
into a single function without generating `CallSiteLoc`.

**Scenario:**
```python
# a.py
def kernel_a(tensor):
    print("a: {}", tensor)  # a.py:3
    jit_func_b(tensor)           # Calls b.py code

# b.py
def func_b(tensor):
    print("b: {}", tensor)  # b.py:7
```

The scenario executes Python at compile-time and directly inserts
operations from `b.py` into the kernel function, resulting in MLIR like:

```mlir
@kernel_a(...) {
  print("a: {}", %arg0) loc(#loc_a)  // a.py:3
  print("b: {}", %arg0) loc(#loc_b)  // b.py:7 <- FileLineColLoc, not CallSiteLoc
} loc(#loc_kernel)  // a.py:1

#loc1 = loc("a.py":3:.)
#loc2 = loc("b.py":7:.)
#loc_a = loc("print"(#loc1))
#loc_b = loc("print"(#loc2))
```
```llvm
!6 = !DIFile(filename: "a.py", directory: "...")
!9 = distinct !DISubprogram(name: "...", linkageName: "...", scope: !6, file: !6, line: 13, ...)
!10 = !DILocation(line: 7, column: ., scope: !9)  // Points to kernel's DISubprogram, not correct
```

- Add missing locations, namely 'ErrnoMem', 'TargetMem0', and
'TargetMem1'.

Reland commit fb829bf11feeb53f815a3abf539e63ec3a23ed3d with additional fixes relating to post-merge CI failure

```
/vol/worker/mlir-nvidia/mlir-nvidia-gcc7/llvm.src/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp: In function ‘constexpr llvm::nvvm::CTAGroupKind getNVVMCtaGroupKind(mlir::NVVM::CTAGroupKind)’:
/vol/worker/mlir-nvidia/mlir-nvidia-gcc7/llvm.src/llvm/include/llvm/Support/ErrorHandling.h:165:36: error: call to non-constexpr function ‘void llvm::llvm_unreachable_internal(const char*, const char*, unsigned int)’
   ::llvm::llvm_unreachable_internal(msg, __FILE__, __LINE__)
   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~
/vol/worker/mlir-nvidia/mlir-nvidia-gcc7/llvm.src/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp:73:3: note: in expansion of macro ‘llvm_unreachable’
   llvm_unreachable("unsupported cta_group value");
   ^
```

Reverts llvm/llvm-project#164356

The bots are broken.

This commit adds support for tgen05.mma family of instructions in the NVVM MLIR dialect and lowers to LLVM Intrinsics. Please refer [PTX ISA](https://docs.nvidia.com/cuda/parallel-thread-execution/#tcgen05-mma-instructions) for information

This MR fixes a recent build breakage by this MR:
https://github.com/llvm/llvm-project/pull/166648

(Post-merge build error here:
https://lab.llvm.org/buildbot/#/builders/138/builds/21929)

The `MLIRInferIntRangeInterface` library is now a public dependency of
`MLIRLLVMDialect`.

This MR modifies side effect traits of some integer arithmetic
operations in the LLVM dialect.

Prior to this MR, the LLVM dialect `sdiv` and `udiv` operations were
marked as `Pure` through `tblgen` inheritance of the
`LLVM_ArithmeticOpBase` class. The `Pure` trait allowed incorrect
hoisting of `sdiv`/`udiv` operations by the
`loop-independent-code-motion` pass.

This MR modifies the `sdiv` and `udiv` LLVM operations to have traits
and code motion behavior identical to their counterparts in the `arith`
dialect, which were established by the commit/review below.


https://github.com/llvm/llvm-project/commit/ed39825be48805b174d3177f1d8d41ed84784d18
https://reviews.llvm.org/D137814

This patch adds support for shared::cta as destination space in
the TMA non-tensor copy Op (from global to shared::cta).

* Appropriate verifier checks are added.
* Unit tests are added to verify the lowering.

The related intrinsic changes were merged through PR #167508.

Signed-off-by: Durgadoss R <durgadossr@nvidia.com>

Reland pass and fix linker errors.

---------

Co-authored-by: Maksim Levental <maksim.levental@gmail.com>

Reverts llvm/llvm-project#167608

Broken builder https://lab.llvm.org/buildbot/#/builders/52/builds/12781