[llvm] [AMDGPU] Enable constant offset promotion to immediate FLAT (PR #93884)

via llvm-commits llvm-commits at lists.llvm.org
Thu May 30 15:12:25 PDT 2024


llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: Stanislav Mekhanoshin (rampitec)

<details>
<summary>Changes</summary>

Currently it is only supported for FLAT Global.

---
Full diff: https://github.com/llvm/llvm-project/pull/93884.diff


3 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/SIISelLowering.h (+2-2) 
- (modified) llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp (+14-4) 
- (modified) llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir (+48) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.h b/llvm/lib/Target/AMDGPU/SIISelLowering.h
index 292b17da93583..8b018a649e6a9 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.h
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.h
@@ -223,8 +223,6 @@ class SITargetLowering final : public AMDGPUTargetLowering {
   SDValue performClampCombine(SDNode *N, DAGCombinerInfo &DCI) const;
   SDValue performRcpCombine(SDNode *N, DAGCombinerInfo &DCI) const;
 
-  bool isLegalFlatAddressingMode(const AddrMode &AM, unsigned AddrSpace,
-                                 uint64_t FlatVariant) const;
   bool isLegalMUBUFAddressingMode(const AddrMode &AM) const;
 
   unsigned isCFIntrinsic(const SDNode *Intr) const;
@@ -316,6 +314,8 @@ class SITargetLowering final : public AMDGPUTargetLowering {
                             SmallVectorImpl<Value*> &/*Ops*/,
                             Type *&/*AccessTy*/) const override;
 
+  bool isLegalFlatAddressingMode(const AddrMode &AM, unsigned AddrSpace,
+                                 uint64_t FlatVariant) const;
   bool isLegalGlobalAddressingMode(const AddrMode &AM) const;
   bool isLegalAddressingMode(const DataLayout &DL, const AddrMode &AM, Type *Ty,
                              unsigned AS,
diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index 774920aac2f08..c7c4f3efb410f 100644
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -2055,10 +2055,20 @@ bool SILoadStoreOptimizer::promoteConstantOffsetToImm(
   if (!(MI.mayLoad() ^ MI.mayStore()))
     return false;
 
-  // TODO: Support flat and scratch.
-  if (AMDGPU::getGlobalSaddrOp(MI.getOpcode()) < 0)
+  if (!STM->hasFlatInstOffsets() || !SIInstrInfo::isFLAT(MI))
     return false;
 
+  // TODO: Support FLAT_SCRATCH. Currently code expects 64-bit pointers.
+  if (SIInstrInfo::isFLATScratch(MI))
+    return false;
+
+  unsigned AS = AMDGPUAS::FLAT_ADDRESS;
+  uint64_t FlatVariant = SIInstrFlags::FLAT;
+  if (SIInstrInfo::isFLATGlobal(MI)) {
+    AS = AMDGPUAS::GLOBAL_ADDRESS;
+    FlatVariant = SIInstrFlags::FlatGlobal;
+  }
+
   if (MI.mayLoad() &&
       TII->getNamedOperand(MI, AMDGPU::OpName::vdata) != nullptr)
     return false;
@@ -2157,7 +2167,7 @@ bool SILoadStoreOptimizer::promoteConstantOffsetToImm(
     TargetLoweringBase::AddrMode AM;
     AM.HasBaseReg = true;
     AM.BaseOffs = Dist;
-    if (TLI->isLegalGlobalAddressingMode(AM) &&
+    if (TLI->isLegalFlatAddressingMode(AM, AS, FlatVariant) &&
         (uint32_t)std::abs(Dist) > MaxDist) {
       MaxDist = std::abs(Dist);
 
@@ -2183,7 +2193,7 @@ bool SILoadStoreOptimizer::promoteConstantOffsetToImm(
       AM.HasBaseReg = true;
       AM.BaseOffs = OtherOffset - AnchorAddr.Offset;
 
-      if (TLI->isLegalGlobalAddressingMode(AM)) {
+      if (TLI->isLegalFlatAddressingMode(AM, AS, FlatVariant)) {
         LLVM_DEBUG(dbgs() << "  Promote Offset(" << OtherOffset; dbgs() << ")";
                    OtherMI->dump());
         updateBaseAndOffset(*OtherMI, Base, OtherOffset - AnchorAddr.Offset);
diff --git a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
index 1a751839e2947..a74faf4ff2c52 100644
--- a/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
+++ b/llvm/test/CodeGen/AMDGPU/promote-constOffset-to-imm.mir
@@ -212,3 +212,51 @@ body:             |
     %13:vreg_64 = REG_SEQUENCE %9, %subreg.sub0, %11, %subreg.sub1
     GLOBAL_STORE_DWORD %13, %0.sub1, 0, 0, implicit $exec
 ...
+---
+
+# GFX9-LABEL: name: diffoporder_add_flat_load
+# GFX9: FLAT_LOAD_DWORD %{{[0-9]+}}, 1000, 0,
+# GFX9: FLAT_LOAD_DWORD %{{[0-9]+}}, 0, 0,
+
+name: diffoporder_add_flat_load
+body:             |
+  bb.0.entry:
+
+    %0:vreg_64 = COPY $vgpr0_vgpr1
+
+    %1:sgpr_32 = S_MOV_B32 4000
+    %2:vgpr_32, %3:sreg_64_xexec = V_ADD_CO_U32_e64 %0.sub0, %1, 0, implicit $exec
+    %4:vgpr_32, dead %5:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %3, 0, implicit $exec
+    %6:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %4, %subreg.sub1
+    %14:vgpr_32 = FLAT_LOAD_DWORD %6, 0, 0, implicit $exec, implicit $flat_scr
+
+    %8:sgpr_32 = S_MOV_B32 3000
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADD_CO_U32_e64 %0.sub0, %8, 0, implicit $exec
+    %11:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %10, 0, implicit $exec
+    %13:vreg_64 = REG_SEQUENCE %9, %subreg.sub0, %11, %subreg.sub1
+    %15:vgpr_32 = FLAT_LOAD_DWORD %13, 0, 0, implicit $exec, implicit $flat_scr
+...
+---
+
+# GFX9-LABEL: name: diffoporder_add_flat_store
+# GFX9: FLAT_STORE_DWORD %{{[0-9]+}}, %0.sub0, 1000, 0,
+# GFX9: FLAT_STORE_DWORD %{{[0-9]+}}, %0.sub1, 0, 0,
+
+name: diffoporder_add_flat_store
+body:             |
+  bb.0.entry:
+
+    %0:vreg_64 = COPY $vgpr0_vgpr1
+
+    %1:sgpr_32 = S_MOV_B32 4000
+    %2:vgpr_32, %3:sreg_64_xexec = V_ADD_CO_U32_e64 %0.sub0, %1, 0, implicit $exec
+    %4:vgpr_32, dead %5:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %3, 0, implicit $exec
+    %6:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %4, %subreg.sub1
+    FLAT_STORE_DWORD %6, %0.sub0, 0, 0, implicit $exec, implicit $flat_scr
+
+    %8:sgpr_32 = S_MOV_B32 3000
+    %9:vgpr_32, %10:sreg_64_xexec = V_ADD_CO_U32_e64 %0.sub0, %8, 0, implicit $exec
+    %11:vgpr_32, dead %12:sreg_64_xexec = V_ADDC_U32_e64 %0.sub1, 0, %10, 0, implicit $exec
+    %13:vreg_64 = REG_SEQUENCE %9, %subreg.sub0, %11, %subreg.sub1
+    FLAT_STORE_DWORD %13, %0.sub1, 0, 0, implicit $exec, implicit $flat_scr
+...

``````````

</details>


https://github.com/llvm/llvm-project/pull/93884


More information about the llvm-commits mailing list