Propagate Constants for Wave Reduction Intrinsics

Author: easyonaadit

llvm/lib/Analysis/ConstantFolding.cpp

@@ -1647,6 +1647,13 @@ bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) {
   case Intrinsic::amdgcn_perm:
   case Intrinsic::amdgcn_wave_reduce_umin:
   case Intrinsic::amdgcn_wave_reduce_umax:
+  case Intrinsic::amdgcn_wave_reduce_max:
+  case Intrinsic::amdgcn_wave_reduce_min:
+  case Intrinsic::amdgcn_wave_reduce_add:
+  case Intrinsic::amdgcn_wave_reduce_sub:
+  case Intrinsic::amdgcn_wave_reduce_and:
+  case Intrinsic::amdgcn_wave_reduce_or:
+  case Intrinsic::amdgcn_wave_reduce_xor:
   case Intrinsic::amdgcn_s_wqm:
   case Intrinsic::amdgcn_s_quadmask:
   case Intrinsic::amdgcn_s_bitreplicate:
@@ -3520,6 +3527,13 @@ static Constant *ConstantFoldIntrinsicCall2(Intrinsic::ID IntrinsicID, Type *Ty,
       return ConstantInt::get(Ty, C0->abs());
     case Intrinsic::amdgcn_wave_reduce_umin:
     case Intrinsic::amdgcn_wave_reduce_umax:
+    case Intrinsic::amdgcn_wave_reduce_max:
+    case Intrinsic::amdgcn_wave_reduce_min:
+    case Intrinsic::amdgcn_wave_reduce_add:
+    case Intrinsic::amdgcn_wave_reduce_sub:
+    case Intrinsic::amdgcn_wave_reduce_and:
+    case Intrinsic::amdgcn_wave_reduce_or:
+    case Intrinsic::amdgcn_wave_reduce_xor:
       return dyn_cast<Constant>(Operands[0]);
     }
 

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.add.ll

@@ -223,68 +223,34 @@ entry:
 define amdgpu_kernel void @poison_value(ptr addrspace(1) %out, i32 %in) {
 ; GFX8DAGISEL-LABEL: poison_value:
 ; GFX8DAGISEL:       ; %bb.0: ; %entry
-; GFX8DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX8DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX8DAGISEL-NEXT:    v_mov_b32_e32 v0, s0
-; GFX8DAGISEL-NEXT:    v_mov_b32_e32 v1, s1
-; GFX8DAGISEL-NEXT:    flat_store_dword v[0:1], v0
 ; GFX8DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX8GISEL-LABEL: poison_value:
 ; GFX8GISEL:       ; %bb.0: ; %entry
-; GFX8GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX8GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX8GISEL-NEXT:    v_mov_b32_e32 v0, s0
-; GFX8GISEL-NEXT:    v_mov_b32_e32 v1, s1
-; GFX8GISEL-NEXT:    flat_store_dword v[0:1], v0
 ; GFX8GISEL-NEXT:    s_endpgm
 ;
 ; GFX9DAGISEL-LABEL: poison_value:
 ; GFX9DAGISEL:       ; %bb.0: ; %entry
-; GFX9DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX9DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9DAGISEL-NEXT:    global_store_dword v0, v0, s[0:1]
 ; GFX9DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX9GISEL-LABEL: poison_value:
 ; GFX9GISEL:       ; %bb.0: ; %entry
-; GFX9GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX9GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX9GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9GISEL-NEXT:    global_store_dword v0, v0, s[0:1]
 ; GFX9GISEL-NEXT:    s_endpgm
 ;
 ; GFX10DAGISEL-LABEL: poison_value:
 ; GFX10DAGISEL:       ; %bb.0: ; %entry
-; GFX10DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX10DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10DAGISEL-NEXT:    global_store_dword v0, v0, s[0:1]
 ; GFX10DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX10GISEL-LABEL: poison_value:
 ; GFX10GISEL:       ; %bb.0: ; %entry
-; GFX10GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX10GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX10GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10GISEL-NEXT:    global_store_dword v0, v0, s[0:1]
 ; GFX10GISEL-NEXT:    s_endpgm
 ;
 ; GFX11DAGISEL-LABEL: poison_value:
 ; GFX11DAGISEL:       ; %bb.0: ; %entry
-; GFX11DAGISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX11DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX11DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11DAGISEL-NEXT:    global_store_b32 v0, v0, s[0:1]
 ; GFX11DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX11GISEL-LABEL: poison_value:
 ; GFX11GISEL:       ; %bb.0: ; %entry
-; GFX11GISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX11GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX11GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11GISEL-NEXT:    global_store_b32 v0, v0, s[0:1]
 ; GFX11GISEL-NEXT:    s_endpgm
 entry:
   %result = call i32 @llvm.amdgcn.wave.reduce.and.i32(i32 poison, i32 1)
@@ -1113,11 +1079,10 @@ define amdgpu_kernel void @const_value_i64(ptr addrspace(1) %out) {
 ; GFX9DAGISEL-LABEL: const_value_i64:
 ; GFX9DAGISEL:       ; %bb.0: ; %entry
 ; GFX9DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v1, 0
-; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v2, 0
+; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX9DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9DAGISEL-NEXT:    global_store_dwordx2 v2, v[0:1], s[0:1]
+; GFX9DAGISEL-NEXT:    global_store_dwordx2 v1, v[0:1], s[0:1]
 ; GFX9DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX9GISEL-LABEL: const_value_i64:
@@ -1133,11 +1098,10 @@ define amdgpu_kernel void @const_value_i64(ptr addrspace(1) %out) {
 ; GFX10DAGISEL-LABEL: const_value_i64:
 ; GFX10DAGISEL:       ; %bb.0: ; %entry
 ; GFX10DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v1, 0
-; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v2, 0
+; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX10DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10DAGISEL-NEXT:    global_store_dwordx2 v2, v[0:1], s[0:1]
+; GFX10DAGISEL-NEXT:    global_store_dwordx2 v1, v[0:1], s[0:1]
 ; GFX10DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX10GISEL-LABEL: const_value_i64:
@@ -1153,11 +1117,10 @@ define amdgpu_kernel void @const_value_i64(ptr addrspace(1) %out) {
 ; GFX1164DAGISEL-LABEL: const_value_i64:
 ; GFX1164DAGISEL:       ; %bb.0: ; %entry
 ; GFX1164DAGISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX1164DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX1164DAGISEL-NEXT:    v_mov_b32_e32 v1, 0
-; GFX1164DAGISEL-NEXT:    v_mov_b32_e32 v2, 0
+; GFX1164DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GFX1164DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX1164DAGISEL-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
+; GFX1164DAGISEL-NEXT:    global_store_b64 v1, v[0:1], s[0:1]
 ; GFX1164DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX1164GISEL-LABEL: const_value_i64:
@@ -1173,10 +1136,9 @@ define amdgpu_kernel void @const_value_i64(ptr addrspace(1) %out) {
 ; GFX1132DAGISEL-LABEL: const_value_i64:
 ; GFX1132DAGISEL:       ; %bb.0: ; %entry
 ; GFX1132DAGISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX1132DAGISEL-NEXT:    v_mov_b32_e32 v0, 0x7b
-; GFX1132DAGISEL-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0
+; GFX1132DAGISEL-NEXT:    v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v0, 0x7b
 ; GFX1132DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX1132DAGISEL-NEXT:    global_store_b64 v2, v[0:1], s[0:1]
+; GFX1132DAGISEL-NEXT:    global_store_b64 v1, v[0:1], s[0:1]
 ; GFX1132DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX1132GISEL-LABEL: const_value_i64:
@@ -1196,68 +1158,34 @@ entry:
 define amdgpu_kernel void @poison_value_i64(ptr addrspace(1) %out, i64 %in) {
 ; GFX8DAGISEL-LABEL: poison_value_i64:
 ; GFX8DAGISEL:       ; %bb.0: ; %entry
-; GFX8DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX8DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX8DAGISEL-NEXT:    v_mov_b32_e32 v0, s0
-; GFX8DAGISEL-NEXT:    v_mov_b32_e32 v1, s1
-; GFX8DAGISEL-NEXT:    flat_store_dwordx2 v[0:1], v[0:1]
 ; GFX8DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX8GISEL-LABEL: poison_value_i64:
 ; GFX8GISEL:       ; %bb.0: ; %entry
-; GFX8GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX8GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX8GISEL-NEXT:    v_mov_b32_e32 v0, s0
-; GFX8GISEL-NEXT:    v_mov_b32_e32 v1, s1
-; GFX8GISEL-NEXT:    flat_store_dwordx2 v[0:1], v[0:1]
 ; GFX8GISEL-NEXT:    s_endpgm
 ;
 ; GFX9DAGISEL-LABEL: poison_value_i64:
 ; GFX9DAGISEL:       ; %bb.0: ; %entry
-; GFX9DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX9DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX9DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9DAGISEL-NEXT:    global_store_dwordx2 v0, v[0:1], s[0:1]
 ; GFX9DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX9GISEL-LABEL: poison_value_i64:
 ; GFX9GISEL:       ; %bb.0: ; %entry
-; GFX9GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX9GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX9GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX9GISEL-NEXT:    global_store_dwordx2 v0, v[0:1], s[0:1]
 ; GFX9GISEL-NEXT:    s_endpgm
 ;
 ; GFX10DAGISEL-LABEL: poison_value_i64:
 ; GFX10DAGISEL:       ; %bb.0: ; %entry
-; GFX10DAGISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX10DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX10DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10DAGISEL-NEXT:    global_store_dwordx2 v0, v[0:1], s[0:1]
 ; GFX10DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX10GISEL-LABEL: poison_value_i64:
 ; GFX10GISEL:       ; %bb.0: ; %entry
-; GFX10GISEL-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x24
-; GFX10GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX10GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX10GISEL-NEXT:    global_store_dwordx2 v0, v[0:1], s[0:1]
 ; GFX10GISEL-NEXT:    s_endpgm
 ;
 ; GFX11DAGISEL-LABEL: poison_value_i64:
 ; GFX11DAGISEL:       ; %bb.0: ; %entry
-; GFX11DAGISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX11DAGISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX11DAGISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11DAGISEL-NEXT:    global_store_b64 v0, v[0:1], s[0:1]
 ; GFX11DAGISEL-NEXT:    s_endpgm
 ;
 ; GFX11GISEL-LABEL: poison_value_i64:
 ; GFX11GISEL:       ; %bb.0: ; %entry
-; GFX11GISEL-NEXT:    s_load_b64 s[0:1], s[4:5], 0x24
-; GFX11GISEL-NEXT:    v_mov_b32_e32 v0, 0
-; GFX11GISEL-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX11GISEL-NEXT:    global_store_b64 v0, v[0:1], s[0:1]
 ; GFX11GISEL-NEXT:    s_endpgm
 entry:
   %result = call i64 @llvm.amdgcn.wave.reduce.and.i64(i64 poison, i32 1)