[LLVM] Make s_getpc_b64 rematerializable

Author: Acim-Maravic

llvm/lib/Target/AMDGPU/SOPInstructions.td

@@ -292,6 +292,7 @@ def S_BITSET0_B64 : SOP1_64_32 <"s_bitset0_b64", [], 1>;
 def S_BITSET1_B32 : SOP1_32    <"s_bitset1_b32", [], 1>;
 def S_BITSET1_B64 : SOP1_64_32 <"s_bitset1_b64", [], 1>;
 
+let isReMaterializable = 1 in
 def S_GETPC_B64 : SOP1_64_0  <"s_getpc_b64",
   [(set i64:$sdst, (int_amdgcn_s_getpc))]
 >;

llvm/test/CodeGen/AMDGPU/remat-sop.mir

@@ -582,14 +582,10 @@ body:             |
 
     ; GCN-LABEL: name: test_remat_s_getpc_b64
     ; GCN: renamable $sgpr0_sgpr1 = S_GETPC_B64
-    ; GCN-NEXT: SI_SPILL_S64_SAVE killed renamable $sgpr0_sgpr1, %stack.1, implicit $exec, implicit $sp_reg :: (store (s64) into %stack.1, align 4, addrspace 5)
     ; GCN-NEXT: renamable $sgpr2_sgpr3 = S_GETPC_B64
-    ; GCN-NEXT: renamable $sgpr0_sgpr1 = S_GETPC_B64
-    ; GCN-NEXT: SI_SPILL_S64_SAVE killed renamable $sgpr0_sgpr1, %stack.0, implicit $exec, implicit $sp_reg :: (store (s64) into %stack.0, align 4, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr0_sgpr1 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sp_reg :: (load (s64) from %stack.1, align 4, addrspace 5)
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0_sgpr1
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr2_sgpr3
-    ; GCN-NEXT: renamable $sgpr0_sgpr1 = SI_SPILL_S64_RESTORE %stack.0, implicit $exec, implicit $sp_reg :: (load (s64) from %stack.0, align 4, addrspace 5)
+    ; GCN-NEXT: renamable $sgpr0_sgpr1 = S_GETPC_B64
     ; GCN-NEXT: S_NOP 0, implicit killed renamable $sgpr0_sgpr1
     ; GCN-NEXT: S_ENDPGM 0
     %0:sgpr_64 = S_GETPC_B64
@@ -610,17 +606,13 @@ body:             |
     ; GCN-LABEL: name: test_remat_s_getpc_b64_2
     ; GCN: renamable $sgpr0_sgpr1 = S_GETPC_B64
     ; GCN-NEXT: renamable $sgpr2_sgpr3 = S_GETPC_B64
-    ; GCN-NEXT: SI_SPILL_S64_SAVE killed renamable $sgpr2_sgpr3, %stack.7, implicit $exec, implicit $sp_reg :: (store (s64) into %stack.7, align 4, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr2_sgpr3 = S_GETPC_B64
-    ; GCN-NEXT: SI_SPILL_S64_SAVE killed renamable $sgpr2_sgpr3, %stack.6, implicit $exec, implicit $sp_reg :: (store (s64) into %stack.6, align 4, addrspace 5)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.3, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.3, addrspace 5)
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr1, %stack.0, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.0, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr2_sgpr3 = SI_SPILL_S64_RESTORE %stack.7, implicit $exec, implicit $sp_reg :: (load (s64) from %stack.7, align 4, addrspace 5)
     ; GCN-NEXT: renamable $sgpr1 = COPY renamable $sgpr2
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr1, %stack.1, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.1, addrspace 5)
     ; GCN-NEXT: renamable $sgpr1 = COPY killed renamable $sgpr3
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr1, %stack.2, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.2, addrspace 5)
-    ; GCN-NEXT: renamable $sgpr0_sgpr1 = SI_SPILL_S64_RESTORE %stack.6, implicit $exec, implicit $sp_reg :: (load (s64) from %stack.6, align 4, addrspace 5)
+    ; GCN-NEXT: renamable $sgpr0_sgpr1 = S_GETPC_B64
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.5, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.5, addrspace 5)
     ; GCN-NEXT: renamable $sgpr0 = COPY killed renamable $sgpr1
     ; GCN-NEXT: SI_SPILL_S32_SAVE killed renamable $sgpr0, %stack.4, implicit $exec, implicit $sp_reg :: (store (s32) into %stack.4, addrspace 5)

llvm/test/CodeGen/AMDGPU/s-getpc-b64-remat.ll

@@ -8,29 +8,22 @@ define void @test_remat_s_getpc_b64() {
 ; CHECK-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; CHECK-NEXT:    s_xor_saveexec_b64 s[4:5], -1
 ; CHECK-NEXT:    buffer_store_dword v0, off, s[0:3], s32 ; 4-byte Folded Spill
-; CHECK-NEXT:    buffer_store_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
 ; CHECK-NEXT:    s_mov_b64 exec, s[4:5]
-; CHECK-NEXT:    ; implicit-def: $vgpr1 : SGPR spill to VGPR lane
-; CHECK-NEXT:    s_getpc_b64 s[4:5]
 ; CHECK-NEXT:    v_writelane_b32 v0, s30, 0
-; CHECK-NEXT:    v_writelane_b32 v1, s4, 0
+; CHECK-NEXT:    s_getpc_b64 s[4:5]
 ; CHECK-NEXT:    v_writelane_b32 v0, s31, 1
-; CHECK-NEXT:    v_writelane_b32 v1, s5, 1
 ; CHECK-NEXT:    ;;#ASMSTART
 ; CHECK-NEXT:    ;;#ASMEND
 ; CHECK-NEXT:    ;;#ASMSTART
 ; CHECK-NEXT:    ;;#ASMEND
-; CHECK-NEXT:    v_readlane_b32 s4, v1, 0
-; CHECK-NEXT:    v_readlane_b32 s5, v1, 1
-; CHECK-NEXT:    v_mov_b32_e32 v2, s4
-; CHECK-NEXT:    v_mov_b32_e32 v3, s5
-; CHECK-NEXT:    global_store_dwordx2 v[1:2], v[2:3], off
+; CHECK-NEXT:    s_getpc_b64 s[4:5]
+; CHECK-NEXT:    v_mov_b32_e32 v1, s4
+; CHECK-NEXT:    v_mov_b32_e32 v2, s5
+; CHECK-NEXT:    global_store_dwordx2 v[1:2], v[1:2], off
 ; CHECK-NEXT:    v_readlane_b32 s31, v0, 1
 ; CHECK-NEXT:    v_readlane_b32 s30, v0, 0
-; CHECK-NEXT:    ; kill: killed $vgpr1
 ; CHECK-NEXT:    s_xor_saveexec_b64 s[4:5], -1
 ; CHECK-NEXT:    buffer_load_dword v0, off, s[0:3], s32 ; 4-byte Folded Reload
-; CHECK-NEXT:    buffer_load_dword v1, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
 ; CHECK-NEXT:    s_mov_b64 exec, s[4:5]
 ; CHECK-NEXT:    s_waitcnt vmcnt(0)
 ; CHECK-NEXT:    s_setpc_b64 s[30:31]