[LLVMdev] Missed optimization opportunity with piecewise load shift-or'd together?

[David Nadlinger]

The following piece of IR is a fixed point for opt -std-compile-opts/-O3:

---
target datalayout =
"e-p:64:64:64-S128-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f16:16:16-f32:32:32-f64:64:64-f128:128:128-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: nounwind readonly
define i32 @get32Bits(i8* inreg nocapture readonly %x_arg) #0 {
  %tmp1 = getelementptr inbounds i8* %x_arg, i64 3
  %tmp2 = load i8* %tmp1, align 1
  %tmp3 = zext i8 %tmp2 to i32
  %tmp4 = shl nuw nsw i32 %tmp3, 24
  %tmp6 = getelementptr inbounds i8* %x_arg, i64 2
  %tmp7 = load i8* %tmp6, align 1
  %tmp8 = zext i8 %tmp7 to i32
  %tmp9 = shl nuw nsw i32 %tmp8, 16
  %tmp10 = or i32 %tmp9, %tmp4
  %tmp12 = getelementptr inbounds i8* %x_arg, i64 1
  %tmp13 = load i8* %tmp12, align 1
  %tmp14 = zext i8 %tmp13 to i32
  %tmp15 = shl nuw nsw i32 %tmp14, 8
  %tmp16 = or i32 %tmp10, %tmp15
  %tmp19 = load i8* %x_arg, align 4
  %tmp20 = zext i8 %tmp19 to i32
  %tmp21 = or i32 %tmp16, %tmp20
  ret i32 %tmp21
}

attributes #0 = { nounwind readonly }
---

Is there a reason why this can't be optimized down to a single i32
load based on the IR semantics, or is this just a missed optimization
opportunity?

Thanks,
David