[llvm] AMDGPU/GlobalISel: Permit mapping G_FRAME_INDEX to sgprs (PR #101325)

[Matt Arsenault via llvm-commits]

================
@@ -96,16 +96,29 @@ define void @private_alloca_to_flat(ptr %ptr) {
 ; OPT-NEXT:    store volatile i32 7, ptr [[TMP1]], align 4
 ; OPT-NEXT:    ret void
 ;
-; ASM-LABEL: private_alloca_to_flat:
-; ASM:       ; %bb.0:
-; ASM-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; ASM-NEXT:    s_mov_b64 s[4:5], src_private_base
-; ASM-NEXT:    v_lshrrev_b32_e64 v0, 6, s32
-; ASM-NEXT:    v_mov_b32_e32 v1, s5
-; ASM-NEXT:    v_mov_b32_e32 v2, 7
-; ASM-NEXT:    flat_store_dword v[0:1], v2
-; ASM-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
-; ASM-NEXT:    s_setpc_b64 s[30:31]
+; DAGISEL-ASM-LABEL: private_alloca_to_flat:
+; DAGISEL-ASM:       ; %bb.0:
+; DAGISEL-ASM-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; DAGISEL-ASM-NEXT:    s_mov_b64 s[4:5], src_private_base
+; DAGISEL-ASM-NEXT:    v_lshrrev_b32_e64 v0, 6, s32
----------------
arsenm wrote:

These should generally use vector operations. Nearly all uses will be vector and we have to spend an extra copy to get back to VGPR 

https://github.com/llvm/llvm-project/pull/101325