maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] For amdpal, widen interpolation mode workaround 

Summary:
The interpolation mode workaround ensures that at least one
interpolation mode is enabled in PSInputAddr. It does not also check
PSInputEna on the basis that the user might enable bits in that
depending on run-time state.

However, for amdpal os type, the user does not enable some bits after
compilation based on run-time states; the register values being
generated here are the final ones set in the hardware. Therefore, apply
the workaround to PSInputAddr and PSInputEnable together. (The case
where a bit is set in PSInputAddr but not in PSInputEnable is where the
frontend set up an input arg for a particular interpolation mode, but
nothing uses that input arg. Really we should have an earlier pass that
removes such an arg.)

Reviewers: arsenm, nhaehnle, dstuttard

Subscribers: kzhuravl, wdng, yaxunl, t-tye, llvm-commits

Differential Revision: https://reviews.llvm.org/D37758

llvm-svn: 315591
This commit is contained in:
Tim Renouf 2017-10-12 16:16:41 +00:00
parent 3e0199f7eb
commit c8ffffe462
2 changed files with 46 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
llvm/lib/Target/AMDGPU/SIISelLowering.cpp
View File

@ -1493,14 +1493,31 @@ SDValue SITargetLowering::LowerFormalArguments(
// - At least one of PERSP_* (0xF) or LINEAR_* (0x70) must be enabled.
// - If POS_W_FLOAT (11) is enabled, at least one of PERSP_* must be
// enabled too.
if (CallConv == CallingConv::AMDGPU_PS &&
((Info->getPSInputAddr() & 0x7F) == 0 ||
((Info->getPSInputAddr() & 0xF) == 0 &&
Info->isPSInputAllocated(11)))) {
CCInfo.AllocateReg(AMDGPU::VGPR0);
CCInfo.AllocateReg(AMDGPU::VGPR1);
Info->markPSInputAllocated(0);
Info->markPSInputEnabled(0);
if (CallConv == CallingConv::AMDGPU_PS) {
if ((Info->getPSInputAddr() & 0x7F) == 0 ||
((Info->getPSInputAddr() & 0xF) == 0 &&
Info->isPSInputAllocated(11))) {
CCInfo.AllocateReg(AMDGPU::VGPR0);
CCInfo.AllocateReg(AMDGPU::VGPR1);
Info->markPSInputAllocated(0);
Info->markPSInputEnabled(0);
}
if (Subtarget->isAmdPalOS()) {
// For isAmdPalOS, the user does not enable some bits after compilation
// based on run-time states; the register values being generated here are
// the final ones set in hardware. Therefore we need to apply the
// workaround to PSInputAddr and PSInputEnable together. (The case where
// a bit is set in PSInputAddr but not PSInputEnable is where the
// frontend set up an input arg for a particular interpolation mode, but
// nothing uses that input arg. Really we should have an earlier pass
// that removes such an arg.)
unsigned PsInputBits = Info->getPSInputAddr() & Info->getPSInputEnable();
if ((PsInputBits & 0x7F) == 0 ||
((PsInputBits & 0xF) == 0 &&
(PsInputBits >> 11 & 1)))
Info->markPSInputEnabled(
countTrailingZeros(Info->getPSInputAddr(), ZB_Undefined));
}
}
assert(!Info->hasDispatchPtr() &&

21
llvm/test/CodeGen/AMDGPU/amdpal-psenable.ll Normal file
View File

@ -0,0 +1,21 @@
; RUN: llc -mtriple=amdgcn--amdpal -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -enable-var-scope %s
; This pixel shader does not use the result of its interpolation, so it would
; end up with an interpolation mode set in PSAddr but not PSEnable. This test tests
; the workaround that ensures that an interpolation mode is also set in PSEnable.
; GCN-LABEL: {{^}}amdpal_psenable:
; GCN: .amd_amdgpu_pal_metadata{{.*}}0xa1b3,0x2,0xa1b4,0x2,
define amdgpu_ps void @amdpal_psenable(i32 inreg, i32 inreg, i32 inreg, i32 inreg %m0, <2 x float> %pos) #6 {
%inst23 = extractelement <2 x float> %pos, i32 0
%inst24 = extractelement <2 x float> %pos, i32 1
%inst25 = tail call float @llvm.amdgcn.interp.p1(float %inst23, i32 0, i32 0, i32 %m0)
%inst26 = tail call float @llvm.amdgcn.interp.p2(float %inst25, float %inst24, i32 0, i32 0, i32 %m0)
ret void
}
declare float @llvm.amdgcn.interp.p1(float, i32, i32, i32) #2
declare float @llvm.amdgcn.interp.p2(float, float, i32, i32, i32) #2
attributes #6 = { nounwind "InitialPSInputAddr"="2" }