[AMDGPU] Reland generated test fix-wwm-vgpr-copy.ll (NFC)

Fix issues left over after generation.

Author: perlfu

llvm/test/CodeGen/AMDGPU/fix-wwm-vgpr-copy.ll

@@ -1,9 +1,36 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; NOTE: llvm.amdgcn.wwm is deprecated, use llvm.amdgcn.strict.wwm instead.
 
-; GCN-LABEL: wwm:
 define amdgpu_hs void @wwm(i32 inreg %arg, ptr addrspace(8) inreg %buffer) {
+; GCN-LABEL: wwm:
+; GCN:       ; %bb.0: ; %entry
+; GCN-NEXT:    s_mov_b32 s7, s4
+; GCN-NEXT:    s_mov_b32 s6, s3
+; GCN-NEXT:    s_mov_b32 s5, s2
+; GCN-NEXT:    s_mov_b32 s4, s1
+; GCN-NEXT:    s_mov_b32 s1, 1
+; GCN-NEXT:    v_mov_b32_e32 v0, 4
+; GCN-NEXT:    s_not_b64 exec, exec
+; GCN-NEXT:    v_mov_b32_e32 v0, 1
+; GCN-NEXT:    s_not_b64 exec, exec
+; GCN-NEXT:    s_or_saveexec_b64 s[2:3], -1
+; GCN-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GCN-NEXT:    s_mov_b64 exec, s[2:3]
+; GCN-NEXT:    s_cmp_lg_u32 s0, 0
+; GCN-NEXT:    v_mov_b32_e32 v1, v0
+; GCN-NEXT:    s_cbranch_scc0 .LBB0_2
+; GCN-NEXT:  ; %bb.1: ; %bb42
+; GCN-NEXT:    s_mov_b32 s1, 0
+; GCN-NEXT:  .LBB0_2: ; %bb602
+; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, s1, v1
+; GCN-NEXT:    s_cbranch_vccnz .LBB0_4
+; GCN-NEXT:  ; %bb.3: ; %bb49
+; GCN-NEXT:    v_mov_b32_e32 v1, 1.0
+; GCN-NEXT:    tbuffer_store_format_x v1, off, s[4:7], 1 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offset:4 glc
+; GCN-NEXT:  .LBB0_4: ; %bb54
+; GCN-NEXT:    s_endpgm
 entry:
   br label %work
 
@@ -23,24 +50,44 @@ bb54:
   ret void
 
 work:
-; GCN: s_not_b64 exec, exec
-; GCN: v_mov_b32_e32 v[[tmp1189:[0-9]+]], 1
-; GCN: s_not_b64 exec, exec
   %tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
 
-; GCN: s_or_saveexec_b64 s[[[LO:[0-9]+]]:[[HI:[0-9]+]]], -1
-; GCN: v_lshlrev_b32_e32 v[[tmp1191:[0-9]+]], 2, v[[tmp1189]]
   %tmp1191 = mul i32 %tmp1189, 4
 
-; GCN: s_mov_b64 exec, s[[[LO]]:[[HI]]]
   %tmp1196 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp1191)
 
   %tmp34 = icmp eq i32 %arg, 0
   br i1 %tmp34, label %bb602, label %bb42
 }
 
-; GCN-LABEL: strict_wwm:
 define amdgpu_hs void @strict_wwm(i32 inreg %arg, ptr addrspace(8) inreg %buffer) {
+; GCN-LABEL: strict_wwm:
+; GCN:       ; %bb.0: ; %entry
+; GCN-NEXT:    s_mov_b32 s7, s4
+; GCN-NEXT:    s_mov_b32 s6, s3
+; GCN-NEXT:    s_mov_b32 s5, s2
+; GCN-NEXT:    s_mov_b32 s4, s1
+; GCN-NEXT:    s_mov_b32 s1, 1
+; GCN-NEXT:    v_mov_b32_e32 v0, 4
+; GCN-NEXT:    s_not_b64 exec, exec
+; GCN-NEXT:    v_mov_b32_e32 v0, 1
+; GCN-NEXT:    s_not_b64 exec, exec
+; GCN-NEXT:    s_or_saveexec_b64 s[2:3], -1
+; GCN-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GCN-NEXT:    s_mov_b64 exec, s[2:3]
+; GCN-NEXT:    s_cmp_lg_u32 s0, 0
+; GCN-NEXT:    v_mov_b32_e32 v1, v0
+; GCN-NEXT:    s_cbranch_scc0 .LBB1_2
+; GCN-NEXT:  ; %bb.1: ; %bb42
+; GCN-NEXT:    s_mov_b32 s1, 0
+; GCN-NEXT:  .LBB1_2: ; %bb602
+; GCN-NEXT:    v_cmp_ne_u32_e32 vcc, s1, v1
+; GCN-NEXT:    s_cbranch_vccnz .LBB1_4
+; GCN-NEXT:  ; %bb.3: ; %bb49
+; GCN-NEXT:    v_mov_b32_e32 v1, 1.0
+; GCN-NEXT:    tbuffer_store_format_x v1, off, s[4:7], 1 format:[BUF_DATA_FORMAT_32,BUF_NUM_FORMAT_FLOAT] offset:4 glc
+; GCN-NEXT:  .LBB1_4: ; %bb54
+; GCN-NEXT:    s_endpgm
 entry:
   br label %work
 
@@ -60,16 +107,10 @@ bb54:
   ret void
 
 work:
-; GCN: s_not_b64 exec, exec
-; GCN: v_mov_b32_e32 v[[tmp1189:[0-9]+]], 1
-; GCN: s_not_b64 exec, exec
   %tmp1189 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 4, i32 1)
 
-; GCN: s_or_saveexec_b64 s[[[LO:[0-9]+]]:[[HI:[0-9]+]]], -1
-; GCN: v_lshlrev_b32_e32 v[[tmp1191:[0-9]+]], 2, v[[tmp1189]]
   %tmp1191 = mul i32 %tmp1189, 4
 
-; GCN: s_mov_b64 exec, s[[[LO]]:[[HI]]]
   %tmp1196 = tail call i32 @llvm.amdgcn.strict.wwm.i32(i32 %tmp1191)
 
   %tmp34 = icmp eq i32 %arg, 0