llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-amdgpu Author: Aaditya (easyonaadit) <details> <summary>Changes</summary> Supporting Arithemtic Operations: `and`, `or`, `xor` --- Patch is 146.75 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/151310.diff 5 Files Affected: - (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+72-6) - (modified) llvm/lib/Target/AMDGPU/SIInstructions.td (+3) - (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll (+854) - (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.or.ll (+855) - (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.xor.ll (+1413) ``````````diff diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp index 56d8e739b6493..c8a0372aa0f8a 100644 --- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp +++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp @@ -5111,9 +5111,12 @@ static uint32_t getIdentityValueForWaveReduction(unsigned Opc) { case AMDGPU::S_SUB_I32: case AMDGPU::S_SUB_U64_PSEUDO: case AMDGPU::S_OR_B32: + case AMDGPU::S_OR_B64: case AMDGPU::S_XOR_B32: + case AMDGPU::S_XOR_B64: return std::numeric_limits<uint32_t>::min(); case AMDGPU::S_AND_B32: + case AMDGPU::S_AND_B64: return std::numeric_limits<uint32_t>::max(); default: llvm_unreachable("Unexpected opcode in getIdentityValueForWaveReduction"); @@ -5146,7 +5149,9 @@ static MachineBasicBlock *lowerWaveReduce(MachineInstr &MI, case AMDGPU::S_MAX_I32: case AMDGPU::V_CMP_GT_I64_e64: /*max*/ case AMDGPU::S_AND_B32: - case AMDGPU::S_OR_B32: { + case AMDGPU::S_AND_B64: + case AMDGPU::S_OR_B32: + case AMDGPU::S_OR_B64: { // Idempotent operations. unsigned movOpc = is32BitOpc ? AMDGPU::S_MOV_B32 : AMDGPU::S_MOV_B64; BuildMI(BB, MI, DL, TII->get(movOpc), DstReg).addReg(SrcReg); @@ -5154,6 +5159,7 @@ static MachineBasicBlock *lowerWaveReduce(MachineInstr &MI, break; } case AMDGPU::S_XOR_B32: + case AMDGPU::S_XOR_B64: case AMDGPU::S_ADD_I32: case AMDGPU::S_ADD_U64_PSEUDO: case AMDGPU::S_SUB_I32: @@ -5177,7 +5183,8 @@ static MachineBasicBlock *lowerWaveReduce(MachineInstr &MI, .addReg(ExecMask); switch (Opc) { - case AMDGPU::S_XOR_B32: { + case AMDGPU::S_XOR_B32: + case AMDGPU::S_XOR_B64: { // Performing an XOR operation on a uniform value // depends on the parity of the number of active lanes. // For even parity, the result will be 0, for odd @@ -5189,10 +5196,54 @@ static MachineBasicBlock *lowerWaveReduce(MachineInstr &MI, .addReg(NewAccumulator->getOperand(0).getReg()) .addImm(1) .setOperandDead(3); // Dead scc - BuildMI(BB, MI, DL, TII->get(AMDGPU::S_MUL_I32), DstReg) - .addReg(SrcReg) - .addReg(ParityRegister); - break; + if (is32BitOpc) { + BuildMI(BB, MI, DL, TII->get(AMDGPU::S_MUL_I32), DstReg) + .addReg(SrcReg) + .addReg(ParityRegister); + break; + } else { + Register DestSub0 = + MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass); + Register DestSub1 = + MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass); + Register Op1H_Op0L_Reg = + MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass); + Register CarryReg = + MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass); + + const TargetRegisterClass *SrcRC = MRI.getRegClass(SrcReg); + const TargetRegisterClass *SrcSubRC = + TRI->getSubRegisterClass(SrcRC, AMDGPU::sub0); + + MachineOperand Op1L = TII->buildExtractSubRegOrImm( + MI, MRI, MI.getOperand(1), SrcRC, AMDGPU::sub0, SrcSubRC); + MachineOperand Op1H = TII->buildExtractSubRegOrImm( + MI, MRI, MI.getOperand(1), SrcRC, AMDGPU::sub1, SrcSubRC); + + BuildMI(BB, MI, DL, TII->get(AMDGPU::S_MUL_I32), DestSub0) + .add(Op1L) + .addReg(ParityRegister); + + BuildMI(BB, MI, DL, TII->get(AMDGPU::S_MUL_I32), Op1H_Op0L_Reg) + .add(Op1H) + .addReg(ParityRegister); + + BuildMI(BB, MI, DL, TII->get(AMDGPU::S_MUL_HI_U32), CarryReg) + .add(Op1L) + .addReg(ParityRegister); + + BuildMI(BB, MI, DL, TII->get(AMDGPU::S_ADD_U32), DestSub1) + .addReg(CarryReg) + .addReg(Op1H_Op0L_Reg) + .setOperandDead(3); // Dead scc + + BuildMI(BB, MI, DL, TII->get(TargetOpcode::REG_SEQUENCE), DstReg) + .addReg(DestSub0) + .addImm(AMDGPU::sub0) + .addReg(DestSub1) + .addImm(AMDGPU::sub1); + break; + } } case AMDGPU::S_SUB_I32: { Register NegatedVal = MRI.createVirtualRegister(DstRegClass); @@ -5407,6 +5458,15 @@ static MachineBasicBlock *lowerWaveReduce(MachineInstr &MI, .addReg(LaneValueHiReg) .addImm(AMDGPU::sub1); switch (Opc) { + case ::AMDGPU::S_OR_B64: + case ::AMDGPU::S_AND_B64: + case ::AMDGPU::S_XOR_B64: { + NewAccumulator = BuildMI(*ComputeLoop, I, DL, TII->get(Opc), DstReg) + .addReg(Accumulator->getOperand(0).getReg()) + .addReg(LaneValue->getOperand(0).getReg()) + .setOperandDead(3); // Dead scc + break; + } case AMDGPU::V_CMP_GT_I64_e64: case AMDGPU::V_CMP_GT_U64_e64: case AMDGPU::V_CMP_LT_I64_e64: @@ -5538,10 +5598,16 @@ SITargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI, return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_SUB_U64_PSEUDO); case AMDGPU::WAVE_REDUCE_AND_PSEUDO_B32: return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_AND_B32); + case AMDGPU::WAVE_REDUCE_AND_PSEUDO_B64: + return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_AND_B64); case AMDGPU::WAVE_REDUCE_OR_PSEUDO_B32: return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_OR_B32); + case AMDGPU::WAVE_REDUCE_OR_PSEUDO_B64: + return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_OR_B64); case AMDGPU::WAVE_REDUCE_XOR_PSEUDO_B32: return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_XOR_B32); + case AMDGPU::WAVE_REDUCE_XOR_PSEUDO_B64: + return lowerWaveReduce(MI, *BB, *getSubtarget(), AMDGPU::S_XOR_B64); case AMDGPU::S_UADDO_PSEUDO: case AMDGPU::S_USUBO_PSEUDO: { const DebugLoc &DL = MI.getDebugLoc(); diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td index 64697673fa1b1..9403ec33003f9 100644 --- a/llvm/lib/Target/AMDGPU/SIInstructions.td +++ b/llvm/lib/Target/AMDGPU/SIInstructions.td @@ -347,6 +347,9 @@ defvar Operations = [ WaveReduceOp<"max", "I64", i64, SGPR_64, VSrc_b64>, WaveReduceOp<"add", "U64", i64, SGPR_64, VSrc_b64>, WaveReduceOp<"sub", "U64", i64, SGPR_64, VSrc_b64>, + WaveReduceOp<"and", "B64", i64, SGPR_64, VSrc_b64>, + WaveReduceOp<"or", "B64", i64, SGPR_64, VSrc_b64>, + WaveReduceOp<"xor", "B64", i64, SGPR_64, VSrc_b64>, ]; foreach Op = Operations in { diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll index 356b0e73b39e7..55e6189f65675 100644 --- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll +++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.reduce.and.ll @@ -980,3 +980,857 @@ endif: store i32 %combine, ptr addrspace(1) %out ret void } + +define amdgpu_kernel void @uniform_value_i64(ptr addrspace(1) %out, i64 %in) { +; GFX8DAGISEL-LABEL: uniform_value_i64: +; GFX8DAGISEL: ; %bb.0: ; %entry +; GFX8DAGISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX8DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v2, s2 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v0, s0 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v1, s1 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v3, s3 +; GFX8DAGISEL-NEXT: flat_store_dwordx2 v[0:1], v[2:3] +; GFX8DAGISEL-NEXT: s_endpgm +; +; GFX8GISEL-LABEL: uniform_value_i64: +; GFX8GISEL: ; %bb.0: ; %entry +; GFX8GISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX8GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX8GISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX8GISEL-NEXT: v_mov_b32_e32 v3, s1 +; GFX8GISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX8GISEL-NEXT: v_mov_b32_e32 v2, s0 +; GFX8GISEL-NEXT: flat_store_dwordx2 v[2:3], v[0:1] +; GFX8GISEL-NEXT: s_endpgm +; +; GFX9DAGISEL-LABEL: uniform_value_i64: +; GFX9DAGISEL: ; %bb.0: ; %entry +; GFX9DAGISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX9DAGISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX9DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX9DAGISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX9DAGISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX9DAGISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX9DAGISEL-NEXT: s_endpgm +; +; GFX9GISEL-LABEL: uniform_value_i64: +; GFX9GISEL: ; %bb.0: ; %entry +; GFX9GISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX9GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX9GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX9GISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX9GISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX9GISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX9GISEL-NEXT: s_endpgm +; +; GFX10DAGISEL-LABEL: uniform_value_i64: +; GFX10DAGISEL: ; %bb.0: ; %entry +; GFX10DAGISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX10DAGISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX10DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX10DAGISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX10DAGISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX10DAGISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX10DAGISEL-NEXT: s_endpgm +; +; GFX10GISEL-LABEL: uniform_value_i64: +; GFX10GISEL: ; %bb.0: ; %entry +; GFX10GISEL-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x24 +; GFX10GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX10GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX10GISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX10GISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX10GISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX10GISEL-NEXT: s_endpgm +; +; GFX1164DAGISEL-LABEL: uniform_value_i64: +; GFX1164DAGISEL: ; %bb.0: ; %entry +; GFX1164DAGISEL-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 +; GFX1164DAGISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX1164DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1164DAGISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX1164DAGISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX1164DAGISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1164DAGISEL-NEXT: s_endpgm +; +; GFX1164GISEL-LABEL: uniform_value_i64: +; GFX1164GISEL: ; %bb.0: ; %entry +; GFX1164GISEL-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 +; GFX1164GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX1164GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1164GISEL-NEXT: v_mov_b32_e32 v0, s2 +; GFX1164GISEL-NEXT: v_mov_b32_e32 v1, s3 +; GFX1164GISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1164GISEL-NEXT: s_endpgm +; +; GFX1132DAGISEL-LABEL: uniform_value_i64: +; GFX1132DAGISEL: ; %bb.0: ; %entry +; GFX1132DAGISEL-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 +; GFX1132DAGISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX1132DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1132DAGISEL-NEXT: v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3 +; GFX1132DAGISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1132DAGISEL-NEXT: s_endpgm +; +; GFX1132GISEL-LABEL: uniform_value_i64: +; GFX1132GISEL: ; %bb.0: ; %entry +; GFX1132GISEL-NEXT: s_load_b128 s[0:3], s[4:5], 0x24 +; GFX1132GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX1132GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1132GISEL-NEXT: v_dual_mov_b32 v0, s2 :: v_dual_mov_b32 v1, s3 +; GFX1132GISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1132GISEL-NEXT: s_endpgm +entry: + %result = call i64 @llvm.amdgcn.wave.reduce.and.i64(i64 %in, i32 1) + store i64 %result, ptr addrspace(1) %out + ret void +} + +define amdgpu_kernel void @const_value_i64(ptr addrspace(1) %out) { +; GFX8DAGISEL-LABEL: const_value_i64: +; GFX8DAGISEL: ; %bb.0: ; %entry +; GFX8DAGISEL-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x24 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v0, 0x7b +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v1, 0 +; GFX8DAGISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v3, s1 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v2, s0 +; GFX8DAGISEL-NEXT: flat_store_dwordx2 v[2:3], v[0:1] +; GFX8DAGISEL-NEXT: s_endpgm +; +; GFX8GISEL-LABEL: const_value_i64: +; GFX8GISEL: ; %bb.0: ; %entry +; GFX8GISEL-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x24 +; GFX8GISEL-NEXT: v_mov_b32_e32 v0, 0x7b +; GFX8GISEL-NEXT: v_mov_b32_e32 v1, 0 +; GFX8GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX8GISEL-NEXT: v_mov_b32_e32 v3, s1 +; GFX8GISEL-NEXT: v_mov_b32_e32 v2, s0 +; GFX8GISEL-NEXT: flat_store_dwordx2 v[2:3], v[0:1] +; GFX8GISEL-NEXT: s_endpgm +; +; 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: s_waitcnt lgkmcnt(0) +; GFX9DAGISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX9DAGISEL-NEXT: s_endpgm +; +; GFX9GISEL-LABEL: const_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, 0x7b +; GFX9GISEL-NEXT: v_mov_b32_e32 v1, 0 +; GFX9GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX9GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX9GISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX9GISEL-NEXT: s_endpgm +; +; 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: s_waitcnt lgkmcnt(0) +; GFX10DAGISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX10DAGISEL-NEXT: s_endpgm +; +; GFX10GISEL-LABEL: const_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, 0x7b +; GFX10GISEL-NEXT: v_mov_b32_e32 v1, 0 +; GFX10GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX10GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX10GISEL-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1] +; GFX10GISEL-NEXT: s_endpgm +; +; 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: s_waitcnt lgkmcnt(0) +; GFX1164DAGISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1164DAGISEL-NEXT: s_endpgm +; +; GFX1164GISEL-LABEL: const_value_i64: +; GFX1164GISEL: ; %bb.0: ; %entry +; GFX1164GISEL-NEXT: s_load_b64 s[0:1], s[4:5], 0x24 +; GFX1164GISEL-NEXT: v_mov_b32_e32 v0, 0x7b +; GFX1164GISEL-NEXT: v_mov_b32_e32 v1, 0 +; GFX1164GISEL-NEXT: v_mov_b32_e32 v2, 0 +; GFX1164GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1164GISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1164GISEL-NEXT: s_endpgm +; +; 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: s_waitcnt lgkmcnt(0) +; GFX1132DAGISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1132DAGISEL-NEXT: s_endpgm +; +; GFX1132GISEL-LABEL: const_value_i64: +; GFX1132GISEL: ; %bb.0: ; %entry +; GFX1132GISEL-NEXT: s_load_b64 s[0:1], s[4:5], 0x24 +; GFX1132GISEL-NEXT: v_mov_b32_e32 v0, 0x7b +; GFX1132GISEL-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_mov_b32 v2, 0 +; GFX1132GISEL-NEXT: s_waitcnt lgkmcnt(0) +; GFX1132GISEL-NEXT: global_store_b64 v2, v[0:1], s[0:1] +; GFX1132GISEL-NEXT: s_endpgm +entry: + %result = call i64 @llvm.amdgcn.wave.reduce.and.i64(i64 123, i32 1) + store i64 %result, ptr addrspace(1) %out + ret void +} + +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) + store i64 %result, ptr addrspace(1) %out + ret void +} + +define void @divergent_value_i64(ptr addrspace(1) %out, i64 %id.x) { +; GFX8DAGISEL-LABEL: divergent_value_i64: +; GFX8DAGISEL: ; %bb.0: ; %entry +; GFX8DAGISEL-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8DAGISEL-NEXT: s_mov_b32 s4, -1 +; GFX8DAGISEL-NEXT: s_mov_b64 s[6:7], exec +; GFX8DAGISEL-NEXT: s_mov_b32 s5, s4 +; GFX8DAGISEL-NEXT: .LBB8_1: ; =>This Inner Loop Header: Depth=1 +; GFX8DAGISEL-NEXT: s_ff1_i32_b64 s10, s[6:7] +; GFX8DAGISEL-NEXT: v_readlane_b32 s8, v2, s10 +; GFX8DAGISEL-NEXT: v_readlane_b32 s9, v3, s10 +; GFX8DAGISEL-NEXT: s_bitset0_b64 s[6:7], s10 +; GFX8DAGISEL-NEXT: s_and_b64 s[4:5], s[4:5], s[8:9] +; GFX8DAGISEL-NEXT: s_cmp_lg_u64 s[6:7], 0 +; GFX8DAGISEL-NEXT: s_cbranch_scc1 .LBB8_1 +; GFX8DAGISEL-NEXT: ; %bb.2: +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v2, s4 +; GFX8DAGISEL-NEXT: v_mov_b32_e32 v3, s5 +; GFX8DAGISEL-NEXT: flat_store_dwordx2 v[0:1], v[2:3] +; GFX8DAGISEL-NEXT: s_waitcnt vmcnt(0) +; GFX8DAGISEL-NEXT: s_setpc_b64 s[30:31] +; +; GFX8GISEL-LABEL: divergent_value_i64: +; GFX8GISEL: ; %bb.0: ; %entry +; GFX8GISEL-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) +; GFX8GISEL-NEXT: s_mov_b32 s4, -1 +; GFX8GISEL-NEXT: s_mov_b64 s[6:7], exec +; GFX8GISEL-NEXT: s_mov_b32 s5, s4 +; GFX8GISEL-NEXT: .LBB8_1: ; =>This Inner Loop Header: Depth=1 +; GFX8GISEL-NEXT: s_ff1_i32_b64 s10, s[6:7] +; GFX8GISEL-NEXT: v_readlane_b32 s8, v... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/151310 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
