[AMDGPU] Omit unnecessary waitcnt before barriers

It is not necessary to wait for all outstanding memory operations before
barriers on hardware that can back off of the barrier in the event of an
exception when traps are enabled. Add a new subtarget feature which
tracks which HW has this ability.

Reviewed By: #amdgpu, rampitec

Differential Revision: https://reviews.llvm.org/D120544

llvm/lib/Target/AMDGPU/AMDGPU.td

@@ -737,6 +737,12 @@ def FeatureAutoWaitcntBeforeBarrier : SubtargetFeature <
   "Hardware automatically inserts waitcnt before barrier"
 >;
 
+def FeatureBackOffBarrier : SubtargetFeature <"back-off-barrier",
+  "BackOffBarrier",
+  "true",
+  "Hardware supports backing off s_barrier if an exception occurs"
+>;
+
 def FeatureTrigReducedRange : SubtargetFeature<"trig-reduced-range",
   "HasTrigReducedRange",
   "true",
@@ -1025,7 +1031,8 @@ def FeatureISAVersion9_0_A : FeatureSet<
    FeatureMadMacF32Insts,
    FeatureSupportsSRAMECC,
    FeaturePackedTID,
-   FullRate64Ops]>;
+   FullRate64Ops,
+   FeatureBackOffBarrier]>;
 
 def FeatureISAVersion9_0_C : FeatureSet<
   [FeatureGFX9,
@@ -1059,7 +1066,8 @@ def FeatureISAVersion9_4_0 : FeatureSet<
    FeatureSupportsSRAMECC,
    FeaturePackedTID,
    FeatureArchitectedFlatScratch,
-   FullRate64Ops]>;
+   FullRate64Ops,
+   FeatureBackOffBarrier]>;
 
 // TODO: Organize more features into groups.
 def FeatureGroup {
@@ -1094,7 +1102,8 @@ def FeatureISAVersion10_1_0 : FeatureSet<
      FeatureMadMacF32Insts,
      FeatureDsSrc2Insts,
      FeatureLdsMisalignedBug,
-     FeatureSupportsXNACK])>;
+     FeatureSupportsXNACK,
+     FeatureBackOffBarrier])>;
 
 def FeatureISAVersion10_1_1 : FeatureSet<
   !listconcat(FeatureGroup.GFX10_1_Bugs,
@@ -1116,7 +1125,8 @@ def FeatureISAVersion10_1_1 : FeatureSet<
      FeatureMadMacF32Insts,
      FeatureDsSrc2Insts,
      FeatureLdsMisalignedBug,
-     FeatureSupportsXNACK])>;
+     FeatureSupportsXNACK,
+     FeatureBackOffBarrier])>;
 
 def FeatureISAVersion10_1_2 : FeatureSet<
   !listconcat(FeatureGroup.GFX10_1_Bugs,
@@ -1138,7 +1148,8 @@ def FeatureISAVersion10_1_2 : FeatureSet<
      FeatureMadMacF32Insts,
      FeatureDsSrc2Insts,
      FeatureLdsMisalignedBug,
-     FeatureSupportsXNACK])>;
+     FeatureSupportsXNACK,
+     FeatureBackOffBarrier])>;
 
 def FeatureISAVersion10_1_3 : FeatureSet<
   !listconcat(FeatureGroup.GFX10_1_Bugs,
@@ -1156,7 +1167,8 @@ def FeatureISAVersion10_1_3 : FeatureSet<
      FeatureMadMacF32Insts,
      FeatureDsSrc2Insts,
      FeatureLdsMisalignedBug,
-     FeatureSupportsXNACK])>;
+     FeatureSupportsXNACK,
+     FeatureBackOffBarrier])>;
 
 def FeatureISAVersion10_3_0 : FeatureSet<
   [FeatureGFX10,
@@ -1173,7 +1185,8 @@ def FeatureISAVersion10_3_0 : FeatureSet<
    FeatureNSAEncoding,
    FeatureNSAMaxSize13,
    FeatureWavefrontSize32,
-   FeatureShaderCyclesRegister]>;
+   FeatureShaderCyclesRegister,
+   FeatureBackOffBarrier]>;
 
 //===----------------------------------------------------------------------===//
 

llvm/lib/Target/AMDGPU/GCNSubtarget.h

@@ -72,6 +72,7 @@ protected:
   // Dynamically set bits that enable features.
   bool FlatForGlobal;
   bool AutoWaitcntBeforeBarrier;
+  bool BackOffBarrier;
   bool UnalignedScratchAccess;
   bool UnalignedAccessMode;
   bool HasApertureRegs;
@@ -493,6 +494,12 @@ public:
     return AutoWaitcntBeforeBarrier;
   }
 
+  /// \returns true if the target supports backing off of s_barrier instructions
+  /// when an exception is raised.
+  bool supportsBackOffBarrier() const {
+    return BackOffBarrier;
+  }
+
   bool hasUnalignedBufferAccess() const {
     return UnalignedBufferAccess;
   }

llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp

@@ -1135,12 +1135,12 @@ bool SIInsertWaitcnts::generateWaitcntInstBefore(
     }
   }
 
-  // Check to see if this is an S_BARRIER, and if an implicit S_WAITCNT 0
+  // The subtarget may have an implicit S_WAITCNT 0 before barriers. If it does
-  // occurs before the instruction. Doing it here prevents any additional
+  // not, we need to ensure the subtarget is capable of backing off barrier
-  // S_WAITCNTs from being emitted if the instruction was marked as
+  // instructions in case there are any outstanding memory operations that may
-  // requiring a WAITCNT beforehand.
+  // cause an exception. Otherwise, insert an explicit S_WAITCNT 0 here.
   if (MI.getOpcode() == AMDGPU::S_BARRIER &&
-      !ST->hasAutoWaitcntBeforeBarrier()) {
+      !ST->hasAutoWaitcntBeforeBarrier() && !ST->supportsBackOffBarrier()) {
     Wait = Wait.combined(AMDGPU::Waitcnt::allZero(ST->hasVscnt()));
   }
 

llvm/test/CodeGen/AMDGPU/back-off-barrier-subtarget-feature.ll

@@ -0,0 +1,97 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9-NO-BACKOFF %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9-BACKOFF %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9-BACKOFF %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -mattr=-back-off-barrier -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX9-NO-BACKOFF %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX10-BACKOFF %s
+
+; Subtargets must wait for outstanding memory instructions before a barrier if
+; they cannot back off of the barrier.
+
+define void @back_off_barrier_no_fence(i32* %in, i32* %out) #0 {
+; GFX9-NO-BACKOFF-LABEL: back_off_barrier_no_fence:
+; GFX9-NO-BACKOFF:       ; %bb.0:
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    s_barrier
+; GFX9-NO-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX9-BACKOFF-LABEL: back_off_barrier_no_fence:
+; GFX9-BACKOFF:       ; %bb.0:
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX9-BACKOFF-NEXT:    s_barrier
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX10-BACKOFF-LABEL: back_off_barrier_no_fence:
+; GFX10-BACKOFF:       ; %bb.0:
+; GFX10-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX10-BACKOFF-NEXT:    s_barrier
+; GFX10-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX10-BACKOFF-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+  %load = load i32, i32* %in
+  call void @llvm.amdgcn.s.barrier()
+  store i32 %load, i32* %out
+  ret void
+}
+
+define void @back_off_barrier_with_fence(i32* %in, i32* %out) #0 {
+; GFX9-NO-BACKOFF-LABEL: back_off_barrier_with_fence:
+; GFX9-NO-BACKOFF:       ; %bb.0:
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    s_barrier
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX9-NO-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-NO-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX9-BACKOFF-LABEL: back_off_barrier_with_fence:
+; GFX9-BACKOFF:       ; %bb.0:
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX9-BACKOFF-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    s_barrier
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX9-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX9-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX10-BACKOFF-LABEL: back_off_barrier_with_fence:
+; GFX10-BACKOFF:       ; %bb.0:
+; GFX10-BACKOFF-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    flat_load_dword v0, v[0:1]
+; GFX10-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    s_barrier
+; GFX10-BACKOFF-NEXT:    s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    buffer_gl0_inv
+; GFX10-BACKOFF-NEXT:    flat_store_dword v[2:3], v0
+; GFX10-BACKOFF-NEXT:    s_waitcnt lgkmcnt(0)
+; GFX10-BACKOFF-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-BACKOFF-NEXT:    s_setpc_b64 s[30:31]
+  %load = load i32, i32* %in
+  fence syncscope("workgroup") release
+  call void @llvm.amdgcn.s.barrier()
+  fence syncscope("workgroup") acquire
+  store i32 %load, i32* %out
+  ret void
+}
+
+declare void @llvm.amdgcn.s.barrier()
+
+attributes #0 = { nounwind }

llvm/test/CodeGen/AMDGPU/waitcnt-preexisting-vscnt.mir

@@ -35,7 +35,7 @@ body:             |
     ; GFX10: S_WAITCNT 0
     ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 0
     ; GFX10: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
-    ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 0
+    ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 1
     ; GFX10: S_BARRIER
     ; GFX10: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
     ; GFX10: S_WAITCNT 112
@@ -112,7 +112,7 @@ body:             |
     ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 0
     ; GFX10: GLOBAL_STORE_DWORD $vgpr0_vgpr1, $vgpr2, 0, 0, implicit $exec
     ; GFX10: S_WAITCNT 0
-    ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 0
+    ; GFX10: S_WAITCNT_VSCNT undef $sgpr_null, 1
     ; GFX10: S_BARRIER
     ; GFX10: $vgpr0 = FLAT_LOAD_DWORD $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
     ; GFX10: S_WAITCNT 112

llvm/test/CodeGen/AMDGPU/waitcnt-vscnt.ll

@@ -1,6 +1,6 @@
 ; RUN: llc -march=amdgcn -mcpu=gfx802  -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX8,GFX8_9 %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900  -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX9,GFX9_10,GFX8_9 %s
-; RUN: llc -march=amdgcn -mcpu=gfx1010 -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX9_10 %s
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-back-off-barrier -asm-verbose=0 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX10,GFX9_10 %s
 
 ; GCN-LABEL: barrier_vmcnt_global:
 ; GFX8:         flat_load_dword
@@ -42,7 +42,7 @@ bb:
   %tmp5 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i64 %tmp4
   store i32 0, i32 addrspace(1)* %tmp5, align 4
   fence syncscope("singlethread") release
-  tail call void @llvm.amdgcn.s.barrier() #3
+  tail call void @llvm.amdgcn.s.barrier()
   fence syncscope("singlethread") acquire
   %tmp6 = add nuw nsw i64 %tmp2, 4294967296
   %tmp7 = lshr exact i64 %tmp6, 32
@@ -116,7 +116,7 @@ bb:
   %tmp5 = getelementptr inbounds i32, i32* %arg, i64 %tmp4
   store i32 0, i32* %tmp5, align 4
   fence syncscope("singlethread") release
-  tail call void @llvm.amdgcn.s.barrier() #3
+  tail call void @llvm.amdgcn.s.barrier()
   fence syncscope("singlethread") acquire
   %tmp6 = add nuw nsw i64 %tmp2, 4294967296
   %tmp7 = lshr exact i64 %tmp6, 32