[AMDGPU] Add attribute for target loop unroll threshold default

Summary:
Add a function attribute to allow the target specific default loop unroll threshold
to be specified on a per-function basis. This allows a front-end to give guidance
where it has insight that is not available to the back-end, while still allowing the
target specific heuristics to also have an effect.

Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D68873

llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

@@ -90,7 +90,8 @@ static bool dependsOnLocalPhi(const Loop *L, const Value *Cond,
 
 void AMDGPUTTIImpl::getUnrollingPreferences(Loop *L, ScalarEvolution &SE,
                                             TTI::UnrollingPreferences &UP) {
-  UP.Threshold = 300; // Twice the default.
+  const Function &F = *L->getHeader()->getParent();
+  UP.Threshold = AMDGPU::getIntegerAttribute(F, "amdgpu-unroll-threshold", 300);
   UP.MaxCount = std::numeric_limits<unsigned>::max();
   UP.Partial = true;
 

llvm/test/CodeGen/AMDGPU/amdgpu-unroll-threshold.ll

@@ -0,0 +1,52 @@
+; RUN: opt < %s -S -mtriple=amdgcn-- -basicaa -loop-unroll | FileCheck %s
+
+; Check that the loop in unroll_default is not fully unrolled using the default
+; unroll threshold
+; CHECK-LABEL: @unroll_default
+; CHECK: entry:
+; CHECK: br i1 %cmp
+; CHECK: ret void
+
+; Check that the same loop in unroll_full is fully unrolled when the default
+; unroll threshold is increased by use of the amdgpu-unroll-threshold attribute
+; CHECK-LABEL: @unroll_full
+; CHECK: entry:
+; CHECK-NOT: br i1 %cmp
+; CHECK: ret void
+
+@in = internal unnamed_addr global i32* null, align 8
+@out = internal unnamed_addr global i32* null, align 8
+
+define void @unroll_default() {
+entry:
+  br label %do.body
+
+do.body:                                          ; preds = %entry
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
+  %v1 = load i64, i64* bitcast (i32** @in to i64*), align 8
+  store i64 %v1, i64* bitcast (i32** @out to i64*), align 8
+  %inc = add nsw i32 %i.0, 1
+  %cmp = icmp slt i32 %inc, 100
+  br i1 %cmp, label %do.body, label %do.end
+
+do.end:                                           ; preds = %do.body
+  ret void
+}
+
+define void @unroll_full() #0 {
+entry:
+  br label %do.body
+
+do.body:                                          ; preds = %entry
+  %i.0 = phi i32 [ 0, %entry ], [ %inc, %do.body ]
+  %v1 = load i64, i64* bitcast (i32** @in to i64*), align 8
+  store i64 %v1, i64* bitcast (i32** @out to i64*), align 8
+  %inc = add nsw i32 %i.0, 1
+  %cmp = icmp slt i32 %inc, 100
+  br i1 %cmp, label %do.body, label %do.end
+
+do.end:                                           ; preds = %do.body
+  ret void
+}
+
+attributes #0 = { "amdgpu-unroll-threshold"="1000" }