AMDGPU: fix local stack slot allocation bugslatest

Summary:
The main bug fix here is using the 32-bit encoding of V_ADD_I32 in
materializeFrameBaseRegister and resolveFrameIndex, so that arbitrary
immediates work.

The second part is that we may now require the SegmentWaveByteOffset
even when there are initially no stack objects and VGPR spilling isn't
enabled, for stack slots that are allocated later. This means that some
bits become effectively dead and can be cleaned up.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=96602

Reviewers: arsenm, tstellarAMD

Subscribers: arsenm, llvm-commits, kzhuravl

Differential Revision: http://reviews.llvm.org/D21551

3 files changed, 35 insertions, 2 deletions

diff --git a/lib/Target/AMDGPU/SIRegisterInfo.cpp b/lib/Target/AMDGPU/SIRegisterInfo.cpp
index 748209bd065..a57f4a0fe91 100644
--- a/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -285,10 +285,13 @@ void SIRegisterInfo::materializeFrameBaseRegister(MachineBasicBlock *MBB,
 
   MachineRegisterInfo &MRI = MF->getRegInfo();
   unsigned UnusedCarry = MRI.createVirtualRegister(&AMDGPU::SReg_64RegClass);
+  unsigned OffsetReg = MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass);
 
+  BuildMI(*MBB, Ins, DL, TII->get(AMDGPU::S_MOV_B32), OffsetReg)
+    .addImm(Offset);
   BuildMI(*MBB, Ins, DL, TII->get(AMDGPU::V_ADD_I32_e64), BaseReg)
     .addReg(UnusedCarry, RegState::Define | RegState::Dead)
-    .addImm(Offset)
+    .addReg(OffsetReg, RegState::Kill)
     .addFrameIndex(FrameIdx);
 }
 
@@ -335,13 +338,16 @@ void SIRegisterInfo::resolveFrameIndex(MachineInstr &MI, unsigned BaseReg,
   assert(Offset != 0 && "Non-zero offset expected");
 
   unsigned UnusedCarry = MRI.createVirtualRegister(&AMDGPU::SReg_64RegClass);
+  unsigned OffsetReg = MRI.createVirtualRegister(&AMDGPU::SReg_32RegClass);
 
   // In the case the instruction already had an immediate offset, here only
   // the requested new offset is added because we are leaving the original
   // immediate in place.
+  BuildMI(*MBB, MI, DL, TII->get(AMDGPU::S_MOV_B32), OffsetReg)
+    .addImm(Offset);
   BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_ADD_I32_e64), NewReg)
     .addReg(UnusedCarry, RegState::Define | RegState::Dead)
-    .addImm(Offset)
+    .addReg(OffsetReg, RegState::Kill)
     .addReg(BaseReg);
 
   FIOp->ChangeToRegister(NewReg, false);
diff --git a/test/CodeGen/AMDGPU/local-stack-slot-bug.ll b/test/CodeGen/AMDGPU/local-stack-slot-bug.ll
new file mode 100644
index 00000000000..46ea1777c28
--- /dev/null
+++ b/test/CodeGen/AMDGPU/local-stack-slot-bug.ll
@@ -0,0 +1,15 @@
+; RUN: llc -march=amdgcn -mcpu=verde -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck %s
+
+; This used to fail due to a v_add_i32 instruction with an illegal immediate
+; operand that was created during Local Stack Slot Allocation. Test case derived
+; from https://bugs.freedesktop.org/show_bug.cgi?id=96602
+;
+; CHECK-LABEL: {{^}}main:
+define amdgpu_ps float @main(i32 %idx) {
+main_body:
+  %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
+  %v2 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0x3FE7A693C0000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFEBE5DC40000000, float 0x3FEBE5DC40000000, float 0xBFEC71C720000000, float 0x3FEC71C6E0000000, float 0xBFEBE5DC60000000, float 0x3FEBE5DC40000000, float 0xBFEA477C20000000, float 0x3FEA477C20000000, float 0xBFE7A693C0000000, float 0x3FE7A69380000000, float 0xBFE41CFEA0000000, float 0xBFDF9B13E0000000, float 0xBFD5C53B80000000, float 0xBFC6326AC0000000, float 0x3EE0789320000000, float 0x3FC6326AC0000000, float 0x3FD5C53B80000000, float 0x3FDF9B13E0000000, float 0x3FE41CFE80000000>, i32 %idx
+  %r = fadd float %v1, %v2
+  ret float %r
+}
diff --git a/test/CodeGen/AMDGPU/selected-stack-object.ll b/test/CodeGen/AMDGPU/selected-stack-object.ll
new file mode 100644
index 00000000000..0519914ee5a
--- /dev/null
+++ b/test/CodeGen/AMDGPU/selected-stack-object.ll
@@ -0,0 +1,12 @@
+; XFAIL: *
+; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck %s
+
+; See also local-stack-slot-bug.ll
+; This fails because a stack object is created during instruction selection.
+
+; CHECK-LABEL: {{^}}main:
+define amdgpu_ps float @main(i32 %idx) {
+main_body:
+  %v1 = extractelement <81 x float> <float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float undef, float 0x3FE41CFEA0000000, float 0xBFE7A693C0000000, float 0xBFEA477C60000000, float 0xBFEBE5DC60000000, float 0xBFEC71C720000000, float 0xBFEBE5DC60000000, float 0xBFEA477C60000000, float 0xBFE7A693C0000000, float 0xBFE41CFEA0000000, float 0x3FDF9B13E0000000, float 0x3FDF9B1380000000, float 0x3FD5C53B80000000, float 0x3FD5C53B00000000, float 0x3FC6326AC0000000, float 0x3FC63269E0000000, float 0xBEE05CEB00000000, float 0xBEE086A320000000, float 0xBFC63269E0000000, float 0xBFC6326AC0000000, float 0xBFD5C53B80000000, float 0xBFD5C53B80000000, float 0xBFDF9B13E0000000, float 0xBFDF9B1460000000, float 0xBFE41CFE80000000, float 0x3FE7A693C0000000, float 0x3FEA477C20000000, float 0x3FEBE5DC40000000, float 0x3FEC71C6E0000000, float 0x3FEBE5DC40000000, float 0x3FEA477C20000000, float 0x3FE7A693C0000000, float 0xBFE41CFE80000000>, i32 %idx
+  ret float %v1
+}