[llvm] [AArch64][SME] Use entry pstate.sm for conditional streaming-mode chnges (PR #152169)

[Benjamin Maxwell via llvm-commits]

================
@@ -3336,18 +3331,19 @@ define i32 @svecc_call_dynamic_alloca(<4 x i16> %P0, i32 %P1, i32 %P2, <vscale x
 ; CHECK64-NEXT:    .cfi_escape 0x10, 0x4e, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 128 - 56 * VG
 ; CHECK64-NEXT:    .cfi_escape 0x10, 0x4f, 0x0b, 0x11, 0x80, 0x7f, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 128 - 64 * VG
 ; CHECK64-NEXT:    sub sp, sp, #64
-; CHECK64-NEXT:    mov w9, w0
-; CHECK64-NEXT:    mov x8, sp
-; CHECK64-NEXT:    mov w2, w1
-; CHECK64-NEXT:    add x9, x9, #15
 ; CHECK64-NEXT:    mov x19, sp
-; CHECK64-NEXT:    and x9, x9, #0x1fffffff0
-; CHECK64-NEXT:    sub x8, x8, x9
+; CHECK64-NEXT:    mov w2, w1
+; CHECK64-NEXT:    mov w8, w0
+; CHECK64-NEXT:    bl __arm_sme_state
----------------
MacDue wrote:

Note: We can use `mrs $var, SVCR` when we have `+sme` which further cleans up code-gen (by not clobbering x0 and x1).  

https://github.com/llvm/llvm-project/pull/152169