[AMDGPU] New intrinsic llvm.amdgcn.pops.exiting.wave.id

This provides access to the special scalar source value
SRC_POPS_EXITING_WAVE_ID on GFX9 and GFX10.

Author: jayfoad

llvm/include/llvm/IR/IntrinsicsAMDGPU.td

@@ -2485,6 +2485,11 @@ class AMDGPUGlobalLoadLDS : Intrinsic <
   "", [SDNPMemOperand]>;
 def int_amdgcn_global_load_lds : AMDGPUGlobalLoadLDS;
 
+// Use read/write of inaccessible memory to model the fact that this reads a
+// volatile value.
+def int_amdgcn_pops_exiting_wave_id :
+  DefaultAttrsIntrinsic<[llvm_i32_ty], [], [IntrInaccessibleMemOnly]>;
+
 //===----------------------------------------------------------------------===//
 // GFX10 Intrinsics
 //===----------------------------------------------------------------------===//

llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp

@@ -5132,6 +5132,8 @@ AMDGPURegisterBankInfo::getInstrMapping(const MachineInstr &MI) const {
       OpdsMapping[2] = getSGPROpMapping(MI.getOperand(2).getReg(), MRI, *TRI);
       break;
     }
+    case Intrinsic::amdgcn_pops_exiting_wave_id:
+      return getDefaultMappingSOP(MI);
     default:
       return getInvalidInstructionMapping();
     }

llvm/lib/Target/AMDGPU/SOPInstructions.td

@@ -213,6 +213,11 @@ let isMoveImm = 1 in {
   } // End Uses = [SCC]
 } // End isMoveImm = 1
 
+// Variant of S_MOV_B32 used for reading volatile source values like
+// SRC_POPS_EXITING_WAVE_ID.
+let mayLoad = 1, mayStore = 1, maybeAtomic = 0 in
+def S_MOV_B32_loadstore : SOP1_32 <"s_mov_b32">;
+
 let Defs = [SCC] in {
   def S_NOT_B32 : SOP1_32 <"s_not_b32",
     [(set i32:$sdst, (UniformUnaryFrag<not> i32:$src0))]
@@ -1865,6 +1870,12 @@ let SubtargetPredicate = isNotGFX9Plus in {
 def : GetFPModePat<fpmode_mask_gfx6plus>;
 }
 
+let SubtargetPredicate = isGFX9GFX10 in
+def : GCNPat<
+  (int_amdgcn_pops_exiting_wave_id),
+  (S_MOV_B32_loadstore (i32 SRC_POPS_EXITING_WAVE_ID))
+>;
+
 //===----------------------------------------------------------------------===//
 // SOP2 Patterns
 //===----------------------------------------------------------------------===//

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.pops.exiting.wave.id.ll

@@ -0,0 +1,34 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefix=SDAG
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck %s -check-prefix=GFX9-GISEL
+; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefix=SDAG
+; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck %s -check-prefix=GFX10-GISEL
+
+define amdgpu_ps void @test(ptr addrspace(1) inreg %ptr) {
+; SDAG-LABEL: test:
+; SDAG:       ; %bb.0:
+; SDAG-NEXT:    s_mov_b32 s2, src_pops_exiting_wave_id
+; SDAG-NEXT:    v_mov_b32_e32 v0, 0
+; SDAG-NEXT:    v_mov_b32_e32 v1, s2
+; SDAG-NEXT:    global_store_dword v0, v1, s[0:1]
+; SDAG-NEXT:    s_endpgm
+;
+; GFX9-GISEL-LABEL: test:
+; GFX9-GISEL:       ; %bb.0:
+; GFX9-GISEL-NEXT:    s_mov_b32 s2, src_pops_exiting_wave_id
+; GFX9-GISEL-NEXT:    v_mov_b32_e32 v0, s2
+; GFX9-GISEL-NEXT:    v_mov_b32_e32 v1, 0
+; GFX9-GISEL-NEXT:    global_store_dword v1, v0, s[0:1]
+; GFX9-GISEL-NEXT:    s_endpgm
+;
+; GFX10-GISEL-LABEL: test:
+; GFX10-GISEL:       ; %bb.0:
+; GFX10-GISEL-NEXT:    s_mov_b32 s2, src_pops_exiting_wave_id
+; GFX10-GISEL-NEXT:    v_mov_b32_e32 v1, 0
+; GFX10-GISEL-NEXT:    v_mov_b32_e32 v0, s2
+; GFX10-GISEL-NEXT:    global_store_dword v1, v0, s[0:1]
+; GFX10-GISEL-NEXT:    s_endpgm
+  %id = call i32 @llvm.amdgcn.pops.exiting.wave.id()
+  store i32 %id, ptr addrspace(1) %ptr
+  ret void
+}