AMDGPU: Propagate amdgpu-waves-per-eu with attributor

This will do a value range merging down the callgraph, unlike the
current pass which can only propagate values to undecorated functions
from a kernel.

This one is a bit weird due to the interaction with the implied range
from amdgpu-flat-workgroup-size. At the default group range of 1,1024,
the minimum implied bounds is 4 so this ends up introducing the
attribute on undecorated functions. We could probably simplify this by
ignoring it and propagating the raw values. The subtarget interaction
and the interaction with amdgpu-flat-workgroup-size only really clamp
invalid values (plus the lower bound doesn't seem to do anything as
far as I can tell anyway).

1 files changed, 14 insertions, 6 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
index e9ce73d5ac8e..9393dee16df2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -416,8 +416,9 @@ std::pair<unsigned, unsigned> AMDGPUSubtarget::getFlatWorkGroupSizes(
   return Requested;
 }
 
-std::pair<unsigned, unsigned> AMDGPUSubtarget::getWavesPerEU(
-    const Function &F, std::pair<unsigned, unsigned> FlatWorkGroupSizes) const {
+std::pair<unsigned, unsigned> AMDGPUSubtarget::getEffectiveWavesPerEU(
+    std::pair<unsigned, unsigned> Requested,
+    std::pair<unsigned, unsigned> FlatWorkGroupSizes) const {
   // Default minimum/maximum number of waves per execution unit.
   std::pair<unsigned, unsigned> Default(1, getMaxWavesPerEU());
 
@@ -429,10 +430,6 @@ std::pair<unsigned, unsigned> AMDGPUSubtarget::getWavesPerEU(
     getWavesPerEUForWorkGroup(FlatWorkGroupSizes.second);
   Default.first = MinImpliedByFlatWorkGroupSize;
 
-  // Requested minimum/maximum number of waves per execution unit.
-  std::pair<unsigned, unsigned> Requested = AMDGPU::getIntegerPairAttribute(
-    F, "amdgpu-waves-per-eu", Default, true);
-
   // Make sure requested minimum is less than requested maximum.
   if (Requested.second && Requested.first > Requested.second)
     return Default;
@@ -450,6 +447,17 @@ std::pair<unsigned, unsigned> AMDGPUSubtarget::getWavesPerEU(
   return Requested;
 }
 
+std::pair<unsigned, unsigned> AMDGPUSubtarget::getWavesPerEU(
+    const Function &F, std::pair<unsigned, unsigned> FlatWorkGroupSizes) const {
+  // Default minimum/maximum number of waves per execution unit.
+  std::pair<unsigned, unsigned> Default(1, getMaxWavesPerEU());
+
+  // Requested minimum/maximum number of waves per execution unit.
+  std::pair<unsigned, unsigned> Requested =
+      AMDGPU::getIntegerPairAttribute(F, "amdgpu-waves-per-eu", Default, true);
+  return getEffectiveWavesPerEU(Requested, FlatWorkGroupSizes);
+}
+
 static unsigned getReqdWorkGroupSize(const Function &Kernel, unsigned Dim) {
   auto Node = Kernel.getMetadata("reqd_work_group_size");
   if (Node && Node->getNumOperands() == 3)