[DirectX] DXILResourceAccess does not correctly handle writes to individual vector elements

[hekota]

DXILResourceAccess does not seem to calculate vector element offset correctly when translating llvm.dx.resource.getpointer & getelementptr & store for a single vector element store.

HLSL:

RWStructuredBuffer<uint4> Out : register(u1);

[numthreads(4, 4, 1)]
void main(uint3 ThreadID : SV_GroupThreadID) {
  Out[0][ThreadID.y] = 111;
}

IR before DXILResourceAccess pass:

; RUN: opt -S -dxil-resource-access -mtriple dxilv1.5-unknown-shadermodel6.5-compute %s

target triple = "dxilv1.5-unknown-shadermodel6.5-compute"

define void @main() local_unnamed_addr {
entry:
  %0 = tail call target("dx.RawBuffer", <4 x i32>, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_v4i32_1_0t(i32 0, i32 1, i32 1, i32 0, ptr null)
  %1 = tail call i32 @llvm.dx.thread.id.in.group(i32 1)
  %2 = tail call noundef nonnull align 16 dereferenceable(16) ptr @llvm.dx.resource.getpointer.p0.tdx.RawBuffer_v4i32_1_0t(target("dx.RawBuffer", <4 x i32>, 1, 0) %0, i32 0)
  %3 = getelementptr i32, ptr %2, i32 %1
  store i32 111, ptr %3, align 4
  ret void
}

IR after DXILResourceAccess pass:

define void @main() local_unnamed_addr {
entry:
  %0 = tail call target("dx.RawBuffer", <4 x i32>, 1, 0) @llvm.dx.resource.handlefrombinding.tdx.RawBuffer_v4i32_1_0t(i32 0, i32 1, i32 1, i32 0, ptr null)
  %1 = tail call i32 @llvm.dx.thread.id.in.group(i32 1)
  call void @llvm.dx.resource.store.rawbuffer.tdx.RawBuffer_v4i32_1_0t.i32(target("dx.RawBuffer", <4 x i32>, 1, 0) %0, i32 0, i32 %1, i32 111)
  ret void
}

The 3rd argument of llvm.dx.resource.store.rawbuffer is element offset and it should be multiplied by size of i32.

Related to #160208