[llvm] [AMDGPU] Support dynamically sized allocas (PR #121148)

via llvm-commits llvm-commits at lists.llvm.org
Thu Dec 26 04:59:45 PST 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-globalisel

@llvm/pr-subscribers-backend-amdgpu

Author: Aaditya (easyonaadit)

<details>
<summary>Changes</summary>

Currently, AMDGPU backend supports static sized allocas. 
This patch extends support for truly dynamic sized allocas. 
The value representing dynamic alloca size can be divergent 
which needs a wave-wide reduction to get the stack space. 
`@<!-- -->llvm.amdgcn.wave.reduce.umax` is used to perform the 
wave reduction.

Note: Compiler already Zero-Extends or Truncates all other 
types(of alloca size arg) to i32.

---

Patch is 98.72 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/121148.diff


6 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp (+8-3) 
- (modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+34-26) 
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-divergent.ll (+255-23) 
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-dyn-stackalloc.mir (+129) 
- (modified) llvm/test/CodeGen/AMDGPU/dynamic_stackalloc.ll (+1287-41) 
- (added) llvm/test/CodeGen/AMDGPU/dynamic_stackalloc_wave_reduce.ll (+170) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
index d94c400ad14225..bdc737958b0e96 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -1190,9 +1190,14 @@ bool AMDGPURegisterBankInfo::applyMappingDynStackAlloc(
 
   const RegisterBank *SizeBank = getRegBank(AllocSize, MRI, *TRI);
 
-  // TODO: Need to emit a wave reduction to get the maximum size.
-  if (SizeBank != &AMDGPU::SGPRRegBank)
-    return false;
+  if (SizeBank != &AMDGPU::SGPRRegBank) {
+    auto WaveReduction =
+        B.buildIntrinsic(Intrinsic::amdgcn_wave_reduce_umax,
+                         {LLT::scalar(MRI.getType(AllocSize).getSizeInBits())})
+            .addUse(AllocSize)
+            .addImm(0);
+    AllocSize = WaveReduction.getReg(0);
+  }
 
   LLT PtrTy = MRI.getType(Dst);
   LLT IntPtrTy = LLT::scalar(PtrTy.getSizeInBits());
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 58b061f5c1af0d..dad743fd00c2ca 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -4017,8 +4017,9 @@ SDValue SITargetLowering::LowerCall(CallLoweringInfo &CLI,
 }
 
 // This is similar to the default implementation in ExpandDYNAMIC_STACKALLOC,
-// except for stack growth direction(default: downwards, AMDGPU: upwards) and
-// applying the wave size scale to the increment amount.
+// except for:
+// 1. stack growth direction(default: downwards, AMDGPU: upwards), and
+// 2. scale size where, scale = wave-reduction(alloca-size) * wave-size
 SDValue SITargetLowering::lowerDYNAMIC_STACKALLOCImpl(SDValue Op,
                                                       SelectionDAG &DAG) const {
   const MachineFunction &MF = DAG.getMachineFunction();
@@ -4026,20 +4027,16 @@ SDValue SITargetLowering::lowerDYNAMIC_STACKALLOCImpl(SDValue Op,
 
   SDLoc dl(Op);
   EVT VT = Op.getValueType();
-  SDValue Tmp1 = Op;
-  SDValue Tmp2 = Op.getValue(1);
-  SDValue Tmp3 = Op.getOperand(2);
-  SDValue Chain = Tmp1.getOperand(0);
-
+  SDValue Chain = Op.getOperand(0);
   Register SPReg = Info->getStackPtrOffsetReg();
 
   // Chain the dynamic stack allocation so that it doesn't modify the stack
   // pointer when other instructions are using the stack.
   Chain = DAG.getCALLSEQ_START(Chain, 0, 0, dl);
 
-  SDValue Size = Tmp2.getOperand(1);
+  SDValue Size = Op.getValue(1).getOperand(1);
   SDValue BaseAddr = DAG.getCopyFromReg(Chain, dl, SPReg, VT);
-  Align Alignment = cast<ConstantSDNode>(Tmp3)->getAlignValue();
+  Align Alignment = cast<ConstantSDNode>(Op.getOperand(2))->getAlignValue();
 
   const TargetFrameLowering *TFL = Subtarget->getFrameLowering();
   assert(TFL->getStackGrowthDirection() == TargetFrameLowering::StackGrowsUp &&
@@ -4057,30 +4054,41 @@ SDValue SITargetLowering::lowerDYNAMIC_STACKALLOCImpl(SDValue Op,
                            DAG.getSignedConstant(-ScaledAlignment, dl, VT));
   }
 
-  SDValue ScaledSize = DAG.getNode(
-      ISD::SHL, dl, VT, Size,
-      DAG.getConstant(Subtarget->getWavefrontSizeLog2(), dl, MVT::i32));
-
-  SDValue NewSP = DAG.getNode(ISD::ADD, dl, VT, BaseAddr, ScaledSize); // Value
+  assert(Size.getValueType() == MVT::i32 && "Size must be 32-bit");
+  SDValue NewSP;
+  if (isa<ConstantSDNode>(Op.getOperand(1))) {
+    // for constant sized alloca, scale alloca size by wave-size
+    SDValue ScaledSize = DAG.getNode(
+        ISD::SHL, dl, VT, Size,
+        DAG.getConstant(Subtarget->getWavefrontSizeLog2(), dl, MVT::i32));
+    NewSP = DAG.getNode(ISD::ADD, dl, VT, BaseAddr, ScaledSize); // Value
+  } else {
+    // for dynamic sized alloca, perform wave-wide reduction to get max of
+    // alloca size(divergent) and then scale it by wave-size
+    SDValue WaveReduction =
+        DAG.getTargetConstant(Intrinsic::amdgcn_wave_reduce_umax, dl, MVT::i32);
+    Size = DAG.getNode(ISD::INTRINSIC_WO_CHAIN, dl, MVT::i32, WaveReduction,
+                       Size, DAG.getConstant(0, dl, MVT::i32));
+    SDValue ScaledSize = DAG.getNode(
+        ISD::SHL, dl, VT, Size,
+        DAG.getConstant(Subtarget->getWavefrontSizeLog2(), dl, MVT::i32));
+    NewSP =
+        DAG.getNode(ISD::ADD, dl, VT, BaseAddr, ScaledSize); // Value in vgpr.
+    SDValue ReadFirstLaneID =
+        DAG.getTargetConstant(Intrinsic::amdgcn_readfirstlane, dl, MVT::i32);
+    NewSP = DAG.getNode(ISD::INTRINSIC_WO_CHAIN, dl, MVT::i32, ReadFirstLaneID,
+                        NewSP);
+  }
 
   Chain = DAG.getCopyToReg(Chain, dl, SPReg, NewSP); // Output chain
-  Tmp2 = DAG.getCALLSEQ_END(Chain, 0, 0, SDValue(), dl);
+  SDValue CallSeqEnd = DAG.getCALLSEQ_END(Chain, 0, 0, SDValue(), dl);
 
-  return DAG.getMergeValues({BaseAddr, Tmp2}, dl);
+  return DAG.getMergeValues({BaseAddr, CallSeqEnd}, dl);
 }
 
 SDValue SITargetLowering::LowerDYNAMIC_STACKALLOC(SDValue Op,
                                                   SelectionDAG &DAG) const {
-  // We only handle constant sizes here to allow non-entry block, static sized
-  // allocas. A truly dynamic value is more difficult to support because we
-  // don't know if the size value is uniform or not. If the size isn't uniform,
-  // we would need to do a wave reduction to get the maximum size to know how
-  // much to increment the uniform stack pointer.
-  SDValue Size = Op.getOperand(1);
-  if (isa<ConstantSDNode>(Size))
-    return lowerDYNAMIC_STACKALLOCImpl(Op, DAG); // Use "generic" expansion.
-
-  return AMDGPUTargetLowering::LowerDYNAMIC_STACKALLOC(Op, DAG);
+  return lowerDYNAMIC_STACKALLOCImpl(Op, DAG); // Use "generic" expansion.
 }
 
 SDValue SITargetLowering::LowerSTACKSAVE(SDValue Op, SelectionDAG &DAG) const {
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-divergent.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-divergent.ll
index aefcad491073fc..a76a125f0580b0 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-divergent.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/dynamic-alloca-divergent.ll
@@ -1,10 +1,38 @@
-; RUN: not llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -global-isel-abort=2 -pass-remarks-missed="gisel.*" -verify-machineinstrs=0 -o /dev/null 2>&1 %s | FileCheck -check-prefix=ERR %s
-
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 1 (in function: kernel_dynamic_stackalloc_vgpr_align4)
-; ERR-NEXT: warning: Instruction selection used fallback path for kernel_dynamic_stackalloc_vgpr_align4
-; ERR-NEXT: error: <unknown>:0:0: in function kernel_dynamic_stackalloc_vgpr_align4 void (ptr addrspace(1)): unsupported dynamic alloca
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefix=GFX9 %s
 
 define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_align4(ptr addrspace(1) %ptr) {
+; GFX9-LABEL: kernel_dynamic_stackalloc_vgpr_align4:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
+; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    s_add_u32 s0, s0, s17
+; GFX9-NEXT:    s_addc_u32 s1, s1, 0
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    global_load_dword v0, v0, s[4:5]
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s33, 0
+; GFX9-NEXT:    s_movk_i32 s32, 0x400
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:  .LBB0_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB0_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_mov_b32 s4, s32
+; GFX9-NEXT:    s_lshl_b32 s5, s6, 6
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
+; GFX9-NEXT:    v_mov_b32_e32 v1, s4
+; GFX9-NEXT:    s_add_u32 s32, s4, s5
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_endpgm
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr i32, ptr addrspace(1) %ptr, i32 %id
   %n = load i32, ptr addrspace(1) %gep
@@ -13,11 +41,38 @@ define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_align4(ptr addrspace(1
   ret void
 }
 
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 1 (in function: kernel_dynamic_stackalloc_vgpr_default_align)
-; ERR-NEXT: warning: Instruction selection used fallback path for kernel_dynamic_stackalloc_vgpr_default_align
-; ERR-NEXT: error: <unknown>:0:0: in function kernel_dynamic_stackalloc_vgpr_default_align void (ptr addrspace(1)): unsupported dynamic alloca
-
 define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_default_align(ptr addrspace(1) %ptr) {
+; GFX9-LABEL: kernel_dynamic_stackalloc_vgpr_default_align:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
+; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    s_add_u32 s0, s0, s17
+; GFX9-NEXT:    s_addc_u32 s1, s1, 0
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    global_load_dword v0, v0, s[4:5]
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s33, 0
+; GFX9-NEXT:    s_movk_i32 s32, 0x400
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:  .LBB1_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB1_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_mov_b32 s4, s32
+; GFX9-NEXT:    s_lshl_b32 s5, s6, 6
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
+; GFX9-NEXT:    v_mov_b32_e32 v1, s4
+; GFX9-NEXT:    s_add_u32 s32, s4, s5
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_endpgm
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr i32, ptr addrspace(1) %ptr, i32 %id
   %n = load i32, ptr addrspace(1) %gep
@@ -25,11 +80,40 @@ define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_default_align(ptr addr
   store volatile i32 123, ptr addrspace(5) %alloca
   ret void
 }
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 64 (in function: kernel_dynamic_stackalloc_vgpr_align64)
-; ERR-NEXT: warning: Instruction selection used fallback path for kernel_dynamic_stackalloc_vgpr_align64
-; ERR-NEXT: error: <unknown>:0:0: in function kernel_dynamic_stackalloc_vgpr_align64 void (ptr addrspace(1)): unsupported dynamic alloca
 
 define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_align64(ptr addrspace(1) %ptr) {
+; GFX9-LABEL: kernel_dynamic_stackalloc_vgpr_align64:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_load_dwordx2 s[4:5], s[8:9], 0x0
+; GFX9-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
+; GFX9-NEXT:    s_add_u32 s0, s0, s17
+; GFX9-NEXT:    s_addc_u32 s1, s1, 0
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NEXT:    global_load_dword v0, v0, s[4:5]
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s33, 0
+; GFX9-NEXT:    s_movk_i32 s32, 0x1000
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:  .LBB2_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB2_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_add_u32 s5, s32, 0xfff
+; GFX9-NEXT:    s_and_b32 s5, s5, 0xfffff000
+; GFX9-NEXT:    s_lshl_b32 s4, s6, 6
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x7b
+; GFX9-NEXT:    v_mov_b32_e32 v1, s5
+; GFX9-NEXT:    s_add_u32 s32, s5, s4
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_endpgm
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr i32, ptr addrspace(1) %ptr, i32 %id
   %n = load i32, ptr addrspace(1) %gep
@@ -38,35 +122,183 @@ define amdgpu_kernel void @kernel_dynamic_stackalloc_vgpr_align64(ptr addrspace(
   ret void
 }
 
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 1 (in function: func_dynamic_stackalloc_vgpr_align4)
-; ERR-NEXT: warning: Instruction selection used fallback path for func_dynamic_stackalloc_vgpr_align4
-; ERR-NEXT: error: <unknown>:0:0: in function func_dynamic_stackalloc_vgpr_align4 void (i32): unsupported dynamic alloca
-
 define void @func_dynamic_stackalloc_vgpr_align4(i32 %n) {
+; GFX9-LABEL: func_dynamic_stackalloc_vgpr_align4:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    s_mov_b32 s9, s33
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_addk_i32 s32, 0x400
+; GFX9-NEXT:  .LBB3_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB3_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_mov_b32 s4, s32
+; GFX9-NEXT:    s_lshl_b32 s5, s6, 6
+; GFX9-NEXT:    s_add_u32 s32, s4, s5
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x1c8
+; GFX9-NEXT:    v_mov_b32_e32 v1, s4
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_addk_i32 s32, 0xfc00
+; GFX9-NEXT:    s_mov_b32 s33, s9
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
   %alloca = alloca i32, i32 %n, align 4, addrspace(5)
   store volatile i32 456, ptr addrspace(5) %alloca
   ret void
 }
 
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 1 (in function: func_dynamic_stackalloc_vgpr_default_align)
-; ERR-NEXT: warning: Instruction selection used fallback path for func_dynamic_stackalloc_vgpr_default_align
-; ERR-NEXT: error: <unknown>:0:0: in function func_dynamic_stackalloc_vgpr_default_align void (i32): unsupported dynamic alloca
-
 define void @func_dynamic_stackalloc_vgpr_default_align(i32 %n) {
+; GFX9-LABEL: func_dynamic_stackalloc_vgpr_default_align:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    s_mov_b32 s9, s33
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_mov_b32 s33, s32
+; GFX9-NEXT:    s_addk_i32 s32, 0x400
+; GFX9-NEXT:  .LBB4_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB4_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_mov_b32 s4, s32
+; GFX9-NEXT:    s_lshl_b32 s5, s6, 6
+; GFX9-NEXT:    s_add_u32 s32, s4, s5
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x1c8
+; GFX9-NEXT:    v_mov_b32_e32 v1, s4
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_addk_i32 s32, 0xfc00
+; GFX9-NEXT:    s_mov_b32 s33, s9
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
   %alloca = alloca i32, i32 %n, addrspace(5)
   store volatile i32 456, ptr addrspace(5) %alloca
   ret void
 }
-; ERR: remark: <unknown>:0:0: cannot select: %{{[0-9]+}}:sreg_32(p5) = G_DYN_STACKALLOC %{{[0-9]+}}:vgpr(s32), 64 (in function: func_dynamic_stackalloc_vgpr_align64)
-; ERR-NEXT: warning: Instruction selection used fallback path for func_dynamic_stackalloc_vgpr_align64
-; ERR-NEXT: error: <unknown>:0:0: in function func_dynamic_stackalloc_vgpr_align64 void (i32): unsupported dynamic alloca
 
 define void @func_dynamic_stackalloc_vgpr_align64(i32 %n) {
+; GFX9-LABEL: func_dynamic_stackalloc_vgpr_align64:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    s_mov_b32 s9, s33
+; GFX9-NEXT:    s_add_i32 s33, s32, 0xfc0
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_and_b32 s33, s33, 0xfffff000
+; GFX9-NEXT:    s_addk_i32 s32, 0x2000
+; GFX9-NEXT:  .LBB5_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB5_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_add_u32 s5, s32, 0xfff
+; GFX9-NEXT:    s_lshl_b32 s4, s6, 6
+; GFX9-NEXT:    s_and_b32 s5, s5, 0xfffff000
+; GFX9-NEXT:    s_add_u32 s32, s5, s4
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x1c8
+; GFX9-NEXT:    v_mov_b32_e32 v1, s5
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_addk_i32 s32, 0xe000
+; GFX9-NEXT:    s_mov_b32 s33, s9
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
   %alloca = alloca i32, i32 %n, align 64, addrspace(5)
   store volatile i32 456, ptr addrspace(5) %alloca
   ret void
 }
 
+define void @func_dynamic_stackalloc_non_standard_size_i64(i64 %n) {
+; GFX9-LABEL: func_dynamic_stackalloc_non_standard_size_i64:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    s_mov_b32 s9, s33
+; GFX9-NEXT:    s_add_i32 s33, s32, 0xfc0
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_and_b32 s33, s33, 0xfffff000
+; GFX9-NEXT:    s_addk_i32 s32, 0x2000
+; GFX9-NEXT:  .LBB6_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB6_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_add_u32 s5, s32, 0xfff
+; GFX9-NEXT:    s_lshl_b32 s4, s6, 6
+; GFX9-NEXT:    s_and_b32 s5, s5, 0xfffff000
+; GFX9-NEXT:    s_add_u32 s32, s5, s4
+; GFX9-NEXT:    v_mov_b32_e32 v0, 0x1c8
+; GFX9-NEXT:    v_mov_b32_e32 v1, s5
+; GFX9-NEXT:    buffer_store_dword v0, v1, s[0:3], 0 offen
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_addk_i32 s32, 0xe000
+; GFX9-NEXT:    s_mov_b32 s33, s9
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
+  %alloca = alloca i32, i64 %n, align 64, addrspace(5)
+  store volatile i32 456, ptr addrspace(5) %alloca
+  ret void
+}
+
+define void @func_dynamic_stackalloc_non_standard_size_i16(i16 %n) {
+; GFX9-LABEL: func_dynamic_stackalloc_non_standard_size_i16:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX9-NEXT:    v_lshl_add_u32 v0, v0, 2, 15
+; GFX9-NEXT:    s_mov_b32 s9, s33
+; GFX9-NEXT:    s_add_i32 s33, s32, 0xfc0
+; GFX9-NEXT:    v_and_b32_e32 v0, -16, v0
+; GFX9-NEXT:    s_mov_b64 s[4:5], exec
+; GFX9-NEXT:    s_mov_b32 s6, 0
+; GFX9-NEXT:    s_and_b32 s33, s33, 0xfffff000
+; GFX9-NEXT:    s_addk_i32 s32, 0x2000
+; GFX9-NEXT:  .LBB7_1: ; =>This Inner Loop Header: Depth=1
+; GFX9-NEXT:    s_ff1_i32_b64 s7, s[4:5]
+; GFX9-NEXT:    v_readlane_b32 s8, v0, s7
+; GFX9-NEXT:    s_bitset0_b64 s[4:5], s7
+; GFX9-NEXT:    s_max_u32 s6, s6, s8
+; GFX9-NEXT:    s_cmp_lg_u64 s[4:5], 0
+; GFX9-NEXT:    s_cbranch_scc1 .LBB7_1
+; GFX9-NEXT:  ; %bb.2:
+; GFX9-NEXT:    s_add_u32 s5, s32, 0xfff
+; GFX9-NEXT:    s_lshl_b32 s4, s6, 6
+; GFX9-NEXT:    s_and_b32 s5, s5, 0xfffff000
+; GF...
[truncated]

``````````

</details>


https://github.com/llvm/llvm-project/pull/121148


More information about the llvm-commits mailing list