[AMDGPU] Still set up the two SGPRs for queue ptr even it is COV5 (ll…

…vm#112403)
kraj · Nov 8, 2024 · e215a1e · e215a1e
1 parent d30a6dc
commit e215a1e
Show file tree

Hide file tree

Showing 571 changed files with 124,086 additions and 133,397 deletions.
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCallLowering.cpp
@@ -465,9 +465,7 @@ static void allocateHSAUserSGPRs(CCState &CCInfo,
     CCInfo.AllocateReg(DispatchPtrReg);
   }
 
-  const Module *M = MF.getFunction().getParent();
-  if (UserSGPRInfo.hasQueuePtr() &&
-      AMDGPU::getAMDHSACodeObjectVersion(*M) < AMDGPU::AMDHSA_COV5) {
+  if (UserSGPRInfo.hasQueuePtr()) {
     Register QueuePtrReg = Info.addQueuePtr(TRI);
     MF.addLiveIn(QueuePtrReg, &AMDGPU::SGPR_64RegClass);
     CCInfo.AllocateReg(QueuePtrReg);

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -2376,9 +2376,7 @@ void SITargetLowering::allocateSpecialInputSGPRs(
   if (UserSGPRInfo.hasDispatchPtr())
     allocateSGPR64Input(CCInfo, ArgInfo.DispatchPtr);
 
-  const Module *M = MF.getFunction().getParent();
-  if (UserSGPRInfo.hasQueuePtr() &&
-      AMDGPU::getAMDHSACodeObjectVersion(*M) < AMDGPU::AMDHSA_COV5)
+  if (UserSGPRInfo.hasQueuePtr())
     allocateSGPR64Input(CCInfo, ArgInfo.QueuePtr);
 
   // Implicit arg ptr takes the place of the kernarg segment pointer. This is a
@@ -2429,9 +2427,7 @@ void SITargetLowering::allocateHSAUserSGPRs(CCState &CCInfo,
     CCInfo.AllocateReg(DispatchPtrReg);
   }
 
-  const Module *M = MF.getFunction().getParent();
-  if (UserSGPRInfo.hasQueuePtr() &&
-      AMDGPU::getAMDHSACodeObjectVersion(*M) < AMDGPU::AMDHSA_COV5) {
+  if (UserSGPRInfo.hasQueuePtr()) {
     Register QueuePtrReg = Info.addQueuePtr(TRI);
     MF.addLiveIn(QueuePtrReg, &AMDGPU::SGPR_64RegClass);
     CCInfo.AllocateReg(QueuePtrReg);

diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/addsubu64.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/addsubu64.ll
@@ -6,28 +6,28 @@ define amdgpu_kernel void @s_add_u64(ptr addrspace(1) %out, i64 %a, i64 %b) {
 ; GFX11-LABEL: s_add_u64:
 ; GFX11:       ; %bb.0: ; %entry
 ; GFX11-NEXT:    s_clause 0x1
-; GFX11-NEXT:    s_load_b128 s[4:7], s[2:3], 0x24
-; GFX11-NEXT:    s_load_b64 s[0:1], s[2:3], 0x34
+; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
 ; GFX11-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-NEXT:    s_add_u32 s0, s6, s0
-; GFX11-NEXT:    s_addc_u32 s1, s7, s1
+; GFX11-NEXT:    s_add_u32 s2, s2, s4
+; GFX11-NEXT:    s_addc_u32 s3, s3, s5
 ; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT:    v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
-; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX11-NEXT:    v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3
+; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
 ; GFX11-NEXT:    s_endpgm
 ;
 ; GFX12-LABEL: s_add_u64:
 ; GFX12:       ; %bb.0: ; %entry
 ; GFX12-NEXT:    s_clause 0x1
-; GFX12-NEXT:    s_load_b128 s[4:7], s[2:3], 0x24
-; GFX12-NEXT:    s_load_b64 s[0:1], s[2:3], 0x34
+; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
 ; GFX12-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    s_add_nc_u64 s[0:1], s[6:7], s[0:1]
+; GFX12-NEXT:    s_add_nc_u64 s[2:3], s[2:3], s[4:5]
 ; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
-; GFX12-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX12-NEXT:    v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3
+; GFX12-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
 ; GFX12-NEXT:    s_endpgm
 entry:
   %add = add i64 %a, %b
@@ -52,28 +52,28 @@ define amdgpu_kernel void @s_sub_u64(ptr addrspace(1) %out, i64 %a, i64 %b) {
 ; GFX11-LABEL: s_sub_u64:
 ; GFX11:       ; %bb.0: ; %entry
 ; GFX11-NEXT:    s_clause 0x1
-; GFX11-NEXT:    s_load_b128 s[4:7], s[2:3], 0x24
-; GFX11-NEXT:    s_load_b64 s[0:1], s[2:3], 0x34
+; GFX11-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX11-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
 ; GFX11-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX11-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11-NEXT:    s_sub_u32 s0, s6, s0
-; GFX11-NEXT:    s_subb_u32 s1, s7, s1
+; GFX11-NEXT:    s_sub_u32 s2, s2, s4
+; GFX11-NEXT:    s_subb_u32 s3, s3, s5
 ; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT:    v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
-; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX11-NEXT:    v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3
+; GFX11-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
 ; GFX11-NEXT:    s_endpgm
 ;
 ; GFX12-LABEL: s_sub_u64:
 ; GFX12:       ; %bb.0: ; %entry
 ; GFX12-NEXT:    s_clause 0x1
-; GFX12-NEXT:    s_load_b128 s[4:7], s[2:3], 0x24
-; GFX12-NEXT:    s_load_b64 s[0:1], s[2:3], 0x34
+; GFX12-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
+; GFX12-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
 ; GFX12-NEXT:    v_mov_b32_e32 v2, 0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    s_sub_nc_u64 s[0:1], s[6:7], s[0:1]
+; GFX12-NEXT:    s_sub_nc_u64 s[2:3], s[2:3], s[4:5]
 ; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
-; GFX12-NEXT:    global_store_b64 v2, v[0:1], s[4:5]
+; GFX12-NEXT:    v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3
+; GFX12-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
 ; GFX12-NEXT:    s_endpgm
 entry:
   %sub = sub i64 %a, %b