[llvm] [RISCV] Enable load clustering by default (PR #73789)

[Pengcheng Wang via llvm-commits]

================
@@ -1085,17 +1085,18 @@ define <4 x i64> @dont_fold_srem_i64(<4 x i64> %x) nounwind {
 ; RV32I-NEXT:    sw s6, 16(sp) # 4-byte Folded Spill
 ; RV32I-NEXT:    sw s7, 12(sp) # 4-byte Folded Spill
 ; RV32I-NEXT:    sw s8, 8(sp) # 4-byte Folded Spill
-; RV32I-NEXT:    lw s0, 24(a1)
-; RV32I-NEXT:    lw s1, 28(a1)
-; RV32I-NEXT:    lw s2, 16(a1)
-; RV32I-NEXT:    lw s3, 20(a1)
+; RV32I-NEXT:    lw s0, 16(a1)
+; RV32I-NEXT:    lw s1, 20(a1)
+; RV32I-NEXT:    lw s2, 24(a1)
+; RV32I-NEXT:    lw s3, 28(a1)
+; RV32I-NEXT:    lw a3, 0(a1)
+; RV32I-NEXT:    lw a4, 4(a1)
 ; RV32I-NEXT:    lw s4, 8(a1)
 ; RV32I-NEXT:    lw s5, 12(a1)
-; RV32I-NEXT:    lw a3, 0(a1)
-; RV32I-NEXT:    lw a1, 4(a1)
 ; RV32I-NEXT:    mv s6, a0
 ; RV32I-NEXT:    li a2, 1
 ; RV32I-NEXT:    mv a0, a3
+; RV32I-NEXT:    mv a1, a4
----------------
wangpc-pp wrote:

Extra move?

https://github.com/llvm/llvm-project/pull/73789