[PATCH] D139852: [amdgpu] Lower CopyToReg into SGPR explicitly to avoid illegal vgpr to sgpr copy

[Jon Chesterfield via Phabricator via llvm-commits]

JonChesterfield added a comment.

Codegen for that test case without this patch applied. Emits an error `error: <unknown>:0:0: in function kern void (ptr): illegal SGPR to VGPR copy` which is also recorded as a comment in the asm.

  kern:                                   ; @kern
  ; %bb.0:
  	s_mov_b32 s32, 0
  	s_add_u32 s12, s12, s17
  	s_addc_u32 s13, s13, 0
  	s_setreg_b32 hwreg(HW_REG_FLAT_SCR_LO), s12
  	s_setreg_b32 hwreg(HW_REG_FLAT_SCR_HI), s13
  	s_add_u32 s0, s0, s17
  	s_addc_u32 s1, s1, 0
  	v_writelane_b32 v40, s16, 0
  	s_mov_b32 s13, s15
  	s_mov_b32 s12, s14
  	v_readlane_b32 s14, v40, 0
  	s_mov_b64 s[16:17], s[8:9]
  	v_mov_b32_e32 v3, v2
  	v_mov_b32_e32 v2, v1
  	v_mov_b32_e32 v1, v0
  	s_load_dwordx2 s[8:9], s[16:17], 0x0
  	v_mov_b32_e32 v0, 42
  	s_waitcnt lgkmcnt(0)
  	v_mov_b32_e32 v4, s8
  	v_mov_b32_e32 v5, s9
  	flat_store_dword v[4:5], v0
  	s_mov_b64 s[18:19], 8
  	s_mov_b32 s8, s16
  	s_mov_b32 s9, s17
  	s_mov_b32 s16, s18
  	s_mov_b32 s15, s19
  	s_add_u32 s8, s8, s16
  	s_addc_u32 s15, s9, s15
          ; kill: def $sgpr8 killed $sgpr8 def $sgpr8_sgpr9
  	s_mov_b32 s9, s15
  	s_getpc_b64 s[16:17]
  	s_add_u32 s16, s16, unknown_call at gotpcrel32@lo+4
  	s_addc_u32 s17, s17, unknown_call at gotpcrel32@hi+12
  	s_load_dwordx2 s[16:17], s[16:17], 0x0
  	s_mov_b64 s[22:23], s[2:3]
  	s_mov_b64 s[20:21], s[0:1]
  	s_mov_b32 s15, 20
  	v_lshlrev_b32_e64 v3, s15, v3
  	s_mov_b32 s15, 10
  	v_lshlrev_b32_e64 v2, s15, v2
  	v_or3_b32 v31, v1, v2, v3
  	 ; illegal copy v0 to s15
  	s_mov_b64 s[0:1], s[20:21]
  	s_mov_b64 s[2:3], s[22:23]
  	s_waitcnt lgkmcnt(0)
  	s_swappc_b64 s[30:31], s[16:17]
  	s_endpgm


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139852/new/

https://reviews.llvm.org/D139852