1024b73ef5
Prepare to accurately track the future denormal-fp-math attribute changes. The way to actually set these separately is not wired in yet. This is just a mechanical change, and mostly still assumes the input and output mode match. This should be refined for some cases. For example, fcanonicalize lowering should use the flushing variant if either input or output flushing is enabled
178 lines
6.1 KiB
LLVM
178 lines
6.1 KiB
LLVM
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -stop-after finalize-isel -o %t.mir %s
|
|
; RUN: llc -run-pass=none -verify-machineinstrs %t.mir -o - | FileCheck %s
|
|
|
|
; Test that SIMachineFunctionInfo can be round trip serialized through
|
|
; MIR.
|
|
|
|
@lds = addrspace(3) global [512 x float] undef, align 4
|
|
|
|
; CHECK-LABEL: {{^}}name: kernel
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK-NEXT: explicitKernArgSize: 128
|
|
; CHECK-NEXT: maxKernArgAlign: 64
|
|
; CHECK-NEXT: ldsSize: 0
|
|
; CHECK-NEXT: isEntryFunction: true
|
|
; CHECK-NEXT: noSignedZerosFPMath: false
|
|
; CHECK-NEXT: memoryBound: false
|
|
; CHECK-NEXT: waveLimiter: false
|
|
; CHECK-NEXT: scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
|
|
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr101'
|
|
; CHECK-NEXT: frameOffsetReg: '$sgpr101'
|
|
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr101'
|
|
; 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: '$vgpr0' }
|
|
; CHECK-NEXT: mode:
|
|
; CHECK-NEXT: ieee: true
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
; CHECK-NEXT: highBitsOf32BitAddress: 0
|
|
; CHECK-NEXT: body:
|
|
define amdgpu_kernel void @kernel(i32 %arg0, i64 %arg1, <16 x i32> %arg2) {
|
|
%gep = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds, i32 0, i32 %arg0
|
|
store float 0.0, float addrspace(3)* %gep, align 4
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: ps_shader
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK-NEXT: explicitKernArgSize: 0
|
|
; CHECK-NEXT: maxKernArgAlign: 1
|
|
; CHECK-NEXT: ldsSize: 0
|
|
; CHECK-NEXT: isEntryFunction: true
|
|
; CHECK-NEXT: noSignedZerosFPMath: false
|
|
; CHECK-NEXT: memoryBound: false
|
|
; CHECK-NEXT: waveLimiter: false
|
|
; CHECK-NEXT: scratchRSrcReg: '$sgpr96_sgpr97_sgpr98_sgpr99'
|
|
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr101'
|
|
; CHECK-NEXT: frameOffsetReg: '$sgpr101'
|
|
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr101'
|
|
; CHECK-NEXT: argumentInfo:
|
|
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr3' }
|
|
; CHECK-NEXT: implicitBufferPtr: { reg: '$sgpr0_sgpr1' }
|
|
; CHECK-NEXT: mode:
|
|
; CHECK-NEXT: ieee: false
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
; CHECK-NEXT: highBitsOf32BitAddress: 0
|
|
; CHECK-NEXT: body:
|
|
define amdgpu_ps void @ps_shader(i32 %arg0, i32 inreg %arg1) {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: function
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK-NEXT: explicitKernArgSize: 0
|
|
; CHECK-NEXT: maxKernArgAlign: 1
|
|
; CHECK-NEXT: ldsSize: 0
|
|
; CHECK-NEXT: isEntryFunction: false
|
|
; CHECK-NEXT: noSignedZerosFPMath: false
|
|
; CHECK-NEXT: memoryBound: false
|
|
; CHECK-NEXT: waveLimiter: false
|
|
; CHECK-NEXT: scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
|
|
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr33'
|
|
; CHECK-NEXT: frameOffsetReg: '$sgpr34'
|
|
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr32'
|
|
; CHECK-NEXT: argumentInfo:
|
|
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
|
|
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr33' }
|
|
; CHECK-NEXT: mode:
|
|
; CHECK-NEXT: ieee: true
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
; CHECK-NEXT: highBitsOf32BitAddress: 0
|
|
; CHECK-NEXT: body:
|
|
define void @function() {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: function_nsz
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK-NEXT: explicitKernArgSize: 0
|
|
; CHECK-NEXT: maxKernArgAlign: 1
|
|
; CHECK-NEXT: ldsSize: 0
|
|
; CHECK-NEXT: isEntryFunction: false
|
|
; CHECK-NEXT: noSignedZerosFPMath: true
|
|
; CHECK-NEXT: memoryBound: false
|
|
; CHECK-NEXT: waveLimiter: false
|
|
; CHECK-NEXT: scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
|
|
; CHECK-NEXT: scratchWaveOffsetReg: '$sgpr33'
|
|
; CHECK-NEXT: frameOffsetReg: '$sgpr34'
|
|
; CHECK-NEXT: stackPtrOffsetReg: '$sgpr32'
|
|
; CHECK-NEXT: argumentInfo:
|
|
; CHECK-NEXT: privateSegmentBuffer: { reg: '$sgpr0_sgpr1_sgpr2_sgpr3' }
|
|
; CHECK-NEXT: privateSegmentWaveByteOffset: { reg: '$sgpr33' }
|
|
; CHECK-NEXT: mode:
|
|
; CHECK-NEXT: ieee: true
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
; CHECK-NEXT: highBitsOf32BitAddress: 0
|
|
; CHECK-NEXT: body:
|
|
define void @function_nsz() #0 {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: function_dx10_clamp_off
|
|
; CHECK: mode:
|
|
; CHECK-NEXT: ieee: true
|
|
; CHECK-NEXT: dx10-clamp: false
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
define void @function_dx10_clamp_off() #1 {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: function_ieee_off
|
|
; CHECK: mode:
|
|
; CHECK-NEXT: ieee: false
|
|
; CHECK-NEXT: dx10-clamp: true
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
define void @function_ieee_off() #2 {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: function_ieee_off_dx10_clamp_off
|
|
; CHECK: mode:
|
|
; CHECK-NEXT: ieee: false
|
|
; CHECK-NEXT: dx10-clamp: false
|
|
; CHECK-NEXT: fp32-input-denormals: false
|
|
; CHECK-NEXT: fp32-output-denormals: false
|
|
; CHECK-NEXT: fp64-fp16-input-denormals: true
|
|
; CHECK-NEXT: fp64-fp16-output-denormals: true
|
|
define void @function_ieee_off_dx10_clamp_off() #3 {
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: {{^}}name: high_address_bits
|
|
; CHECK: machineFunctionInfo:
|
|
; CHECK: highBitsOf32BitAddress: 4294934528
|
|
define amdgpu_ps void @high_address_bits() #4 {
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "no-signed-zeros-fp-math" = "true" }
|
|
attributes #1 = { "amdgpu-dx10-clamp" = "false" }
|
|
attributes #2 = { "amdgpu-ieee" = "false" }
|
|
attributes #3 = { "amdgpu-dx10-clamp" = "false" "amdgpu-ieee" = "false" }
|
|
attributes #4 = { "amdgpu-32bit-address-high-bits"="0xffff8000" }
|