b78b36e1a2
To reduce the register pressure during allocation, when the allocator spills a virtual register that corresponds to a whole wave mode operation, the spill loads and restores should be activated for all lanes by temporarily flipping all bits in exec register to one just before the spills. It is not implemented in the compiler as of today and this patch enables the necessary support. This is a pre-patch before the SGPR spill to virtual VGPR lanes that would eventually causes the whole wave register spills during allocation. Reviewed By: arsenm, cdevadas Differential Revision: https://reviews.llvm.org/D143759
70 lines
2.2 KiB
LLVM
70 lines
2.2 KiB
LLVM
; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -amdgpu-s-branch-bits=4 -stop-after=branch-relaxation -verify-machineinstrs %s -o - | FileCheck %s
|
|
|
|
; Test that long branch reserved register is serialized through
|
|
; MIR.
|
|
|
|
; CHECK-LABEL: {{^}}name: uniform_long_forward_branch
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK-NEXT: explicitKernArgSize: 12
|
|
; CHECK-NEXT: maxKernArgAlign: 8
|
|
; CHECK-NEXT: ldsSize: 0
|
|
; CHECK-NEXT: gdsSize: 0
|
|
; CHECK-NEXT: dynLDSAlign: 1
|
|
; CHECK-NEXT: isEntryFunction: true
|
|
; CHECK-NEXT: noSignedZerosFPMath: false
|
|
; CHECK-NEXT: memoryBound: false
|
|
; CHECK-NEXT: waveLimiter: false
|
|
; CHECK-NEXT: hasSpilledSGPRs: false
|
|
; CHECK-NEXT: hasSpilledVGPRs: false
|
|
; CHECK-NEXT: scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
|
|
; CHECK-NEXT: frameOffsetReg: '$fp_reg'
|
|
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr32'
|
|
; CHECK-NEXT: bytesInStackArgArea: 0
|
|
; CHECK-NEXT: returnsVoid: true
|
|
; CHECK-NEXT: argumentInfo:
|
|
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
|
|
; CHECK-NEXT: kernargSegmentPtr: { reg: '$sgpr4_sgpr5' }
|
|
; CHECK-NEXT: workGroupIDX: { reg: '$sgpr6' }
|
|
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr7' }
|
|
; CHECK-NEXT: workItemIDX: { reg: '$vgpr0' }
|
|
; CHECK-NEXT: psInputAddr: 0
|
|
; CHECK-NEXT: psInputEnable: 0
|
|
; CHECK-NEXT: mode:
|
|
; CHECK-NEXT: ieee: true
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: true
|
|
; CHECK-NEXT: fp32-output-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
; CHECK-NEXT: BitsOf32BitAddress: 0
|
|
; CHECK-NEXT: occupancy: 8
|
|
; CHECK-NEXT: vgprForAGPRCopy: ''
|
|
; CHECK-NEXT: sgprForEXECCopy: '$sgpr100_sgpr101'
|
|
; CHECK-NEXT: longBranchReservedReg: '$sgpr2_sgpr3'
|
|
; CHECK-NEXT: body:
|
|
define amdgpu_kernel void @uniform_long_forward_branch(ptr addrspace(1) %arg, i32 %arg1) {
|
|
bb0:
|
|
%tmp = icmp ne i32 %arg1, 0
|
|
br i1 %tmp, label %bb2, label %bb3
|
|
|
|
bb2:
|
|
store volatile i32 17, ptr addrspace(1) undef
|
|
br label %bb4
|
|
|
|
bb3:
|
|
; 32 byte asm
|
|
call void asm sideeffect
|
|
"v_nop_e64
|
|
v_nop_e64
|
|
v_nop_e64
|
|
v_nop_e64", ""() #0
|
|
br label %bb4
|
|
|
|
bb4:
|
|
store volatile i32 63, ptr addrspace(1) %arg
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|