Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.cpp =================================================================== --- llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.cpp +++ llvm/trunk/lib/Target/AMDGPU/AMDGPUSubtarget.cpp @@ -277,7 +277,7 @@ // Make sure requested values are compatible with values implied by requested // minimum/maximum flat work group sizes. if (RequestedFlatWorkGroupSize && - Requested.first > MinImpliedByFlatWorkGroupSize) + Requested.first < MinImpliedByFlatWorkGroupSize) return Default; return Requested; Index: llvm/trunk/test/CodeGen/AMDGPU/attr-amdgpu-waves-per-eu.ll =================================================================== --- llvm/trunk/test/CodeGen/AMDGPU/attr-amdgpu-waves-per-eu.ll +++ llvm/trunk/test/CodeGen/AMDGPU/attr-amdgpu-waves-per-eu.ll @@ -188,3 +188,15 @@ ret void } attributes #9 = {"amdgpu-waves-per-eu"="10,10"} + +; Exactly 256 workitems and exactly 2 waves. +; CHECK-LABEL: {{^}}empty_workitems_exactly_256_waves_exactly_2: +; CHECK: SGPRBlocks: 12 +; CHECK: VGPRBlocks: 21 +; CHECK: NumSGPRsForWavesPerEU: 102 +; CHECK: NumVGPRsForWavesPerEU: 85 +define amdgpu_kernel void @empty_workitems_exactly_256_waves_exactly_2() #10 { +entry: + ret void +} +attributes #10 = {"amdgpu-flat-work-group-size"="256,256" "amdgpu-waves-per-eu"="2,2"}