[llvm] [IndVarSimplify] Fix `IndVarSimplify` to skip on unfolding predicates when the loop contains control convergence operations. (PR #165643)

[Steven Perron via llvm-commits]

================
@@ -0,0 +1,98 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=indvars -indvars-predicate-loops=1 -S | FileCheck %s
+
+; Loop with body using loop convergence token should be skipped by IndVarSimplify.
+
+%"class.hlsl::RWStructuredBuffer" = type { target("spirv.VulkanBuffer", [0 x i32], 12, 1), target("spirv.VulkanBuffer", i32, 12, 1) }
+
+ at _ZL3Out = internal global %"class.hlsl::RWStructuredBuffer" poison, align 8
+ at .str = private unnamed_addr constant [4 x i8] c"Out\00", align 1
+
+declare token @llvm.experimental.convergence.entry() #0
+
+define void @loop() local_unnamed_addr #1 {
+; CHECK-LABEL: @loop(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = tail call token @llvm.experimental.convergence.entry()
+; CHECK-NEXT:    [[TMP1:%.*]] = tail call target("spirv.VulkanBuffer", [0 x i32], 12, 1) @llvm.spv.resource.handlefrombinding.tspirv.VulkanBuffer_a0i32_12_1t(i32 0, i32 0, i32 1, i32 0, ptr nonnull @.str)
+; CHECK-NEXT:    [[TMP2:%.*]] = tail call target("spirv.VulkanBuffer", i32, 12, 1) @llvm.spv.resource.counterhandlefromimplicitbinding.tspirv.VulkanBuffer_i32_12_1t.tspirv.VulkanBuffer_a0i32_12_1t(target("spirv.VulkanBuffer", [0 x i32], 12, 1) [[TMP1]], i32 0, i32 0)
+; CHECK-NEXT:    store target("spirv.VulkanBuffer", [0 x i32], 12, 1) [[TMP1]], ptr @_ZL3Out, align 8
+; CHECK-NEXT:    store target("spirv.VulkanBuffer", i32, 12, 1) [[TMP2]], ptr getelementptr inbounds nuw (i8, ptr @_ZL3Out, i64 8), align 8
+; CHECK-NEXT:    [[TMP3:%.*]] = tail call i32 @llvm.spv.thread.id.in.group.i32(i32 0)
+; CHECK-NEXT:    br label [[FOR_COND_I:%.*]]
+; CHECK:       for.cond.i:
+; CHECK-NEXT:    [[I_0_I:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INC_I:%.*]], [[FOR_BODY_I:%.*]] ]
+; CHECK-NEXT:    [[TMP4:%.*]] = call token @llvm.experimental.convergence.loop() [ "convergencectrl"(token [[TMP0]]) ]
+; CHECK-NEXT:    [[CMP_I:%.*]] = icmp ult i32 [[I_0_I]], 8
+; CHECK-NEXT:    br i1 [[CMP_I]], label [[FOR_BODY_I]], label [[_Z4LOOPDV3_J_EXIT_LOOPEXIT:%.*]]
+; CHECK:       for.body.i:
+; CHECK-NEXT:    [[CMP1_I:%.*]] = icmp eq i32 [[I_0_I]], [[TMP3]]
+; CHECK-NEXT:    [[INC_I]] = add nuw nsw i32 [[I_0_I]], 1
+; CHECK-NEXT:    br i1 [[CMP1_I]], label [[IF_THEN_I:%.*]], label [[FOR_COND_I]]
+; CHECK:       _Z4loopDv3_j.exit.loopexit:
+; CHECK-NEXT:    br label [[_Z4LOOPDV3_J_EXIT:%.*]]
+; CHECK:       if.then.i:
+; CHECK-NEXT:    [[HLSL_WAVE_ACTIVE_MAX2_I:%.*]] = call spir_func i32 @llvm.spv.wave.reduce.umax.i32(i32 [[TMP3]]) [ "convergencectrl"(token [[TMP4]]) ]
+; CHECK-NEXT:    [[TMP5:%.*]] = tail call noundef align 4 dereferenceable(4) ptr addrspace(11) @llvm.spv.resource.getpointer.p11.tspirv.VulkanBuffer_a0i32_12_1t(target("spirv.VulkanBuffer", [0 x i32], 12, 1) [[TMP1]], i32 [[TMP3]])
+; CHECK-NEXT:    store i32 [[HLSL_WAVE_ACTIVE_MAX2_I]], ptr addrspace(11) [[TMP5]], align 4
+; CHECK-NEXT:    br label [[_Z4LOOPDV3_J_EXIT]]
+; CHECK:       _Z4loopDv3_j.exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %0 = tail call token @llvm.experimental.convergence.entry()
+  %1 = tail call target("spirv.VulkanBuffer", [0 x i32], 12, 1) @llvm.spv.resource.handlefrombinding.tspirv.VulkanBuffer_a0i32_12_1t(i32 0, i32 0, i32 1, i32 0, ptr nonnull @.str)
+  %2 = tail call target("spirv.VulkanBuffer", i32, 12, 1) @llvm.spv.resource.counterhandlefromimplicitbinding.tspirv.VulkanBuffer_i32_12_1t.tspirv.VulkanBuffer_a0i32_12_1t(target("spirv.VulkanBuffer", [0 x i32], 12, 1) %1, i32 0, i32 0)
+  store target("spirv.VulkanBuffer", [0 x i32], 12, 1) %1, ptr @_ZL3Out, align 8
+  store target("spirv.VulkanBuffer", i32, 12, 1) %2, ptr getelementptr inbounds nuw (i8, ptr @_ZL3Out, i64 8), align 8
+  %3 = tail call i32 @llvm.spv.thread.id.in.group.i32(i32 0)
----------------
s-perron wrote:

Replace this with an input to the function.

https://github.com/llvm/llvm-project/pull/165643