[llvm] [RFC][AMDGPU] Remove old llvm.amdgcn.buffer.* and tbuffer intrinsics (PR #93801)

[Matt Arsenault via llvm-commits]

================
@@ -1,93 +0,0 @@
-; RUN: llc < %s -mtriple=amdgcn -mcpu=gfx90a -verify-machineinstrs | FileCheck %s -check-prefix=GFX90A
-; RUN: not --crash llc < %s -mtriple=amdgcn -mcpu=gfx908 -verify-machineinstrs 2>&1 | FileCheck %s -check-prefix=GFX908
-
-declare float @llvm.amdgcn.buffer.atomic.fadd.f32(float, <4 x i32>, i32, i32, i1)
-declare <2 x half> @llvm.amdgcn.buffer.atomic.fadd.v2f16(<2 x half>, <4 x i32>, i32, i32, i1)
-declare float @llvm.amdgcn.global.atomic.fadd.f32.p1.f32(ptr addrspace(1), float)
----------------
arsenm wrote:

We're missing run lines in other tests, I'll deal with this 

https://github.com/llvm/llvm-project/pull/93801