From 494b8ac95a79031fc19266dea42d29e140444b47 Mon Sep 17 00:00:00 2001
From: Carl Ritson <carl.ritson@amd.com>
Date: Fri, 8 Feb 2019 15:41:11 +0000
Subject: [PATCH] [AMDGPU] Fix CS scratch setup on pre-GCN3 ASICs

Summary:
Prior to GCN3 s_load_dword offsets are in dwords rather than bytes.
Thus the scratch buffer descriptor offset must be adjusted for pre-GCN3 ASICs.

Reviewers: nhaehnle, tpr

Reviewed By: nhaehnle

Subscribers: sheredom, arsenm, kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, jfb, llvm-commits

Differential Revision: https://reviews.llvm.org/D56496

llvm-svn: 353530
---
 llvm/lib/Target/AMDGPU/SIFrameLowering.cpp | 4 +++-
 llvm/test/CodeGen/AMDGPU/amdpal.ll         | 7 +++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
index 175e2bd84a21..536884704006 100644
--- a/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFrameLowering.cpp
@@ -422,9 +422,11 @@ void SIFrameLowering::emitEntryFunctionScratchSetup(const GCNSubtarget &ST,
                                        MachineMemOperand::MODereferenceable,
                                        16, 4);
     unsigned Offset = Fn.getCallingConv() == CallingConv::AMDGPU_CS ? 16 : 0;
+    const GCNSubtarget &Subtarget = MF.getSubtarget<GCNSubtarget>();
+    unsigned EncodedOffset = AMDGPU::getSMRDEncodedOffset(Subtarget, Offset);
     BuildMI(MBB, I, DL, LoadDwordX4, ScratchRsrcReg)
       .addReg(Rsrc01)
-      .addImm(Offset) // offset
+      .addImm(EncodedOffset) // offset
       .addImm(0) // glc
       .addReg(ScratchRsrcReg, RegState::ImplicitDefine)
       .addMemOperand(MMO);
diff --git a/llvm/test/CodeGen/AMDGPU/amdpal.ll b/llvm/test/CodeGen/AMDGPU/amdpal.ll
index 8d4c09cdeaf5..c6d082ded048 100644
--- a/llvm/test/CodeGen/AMDGPU/amdpal.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdpal.ll
@@ -1,4 +1,5 @@
-; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=tahiti | FileCheck --check-prefix=PAL --enable-var-scope %s
+; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=tahiti | FileCheck --check-prefixes=PAL,CI --enable-var-scope %s
+; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=tonga | FileCheck --check-prefixes=PAL,VI --enable-var-scope %s
 
 ; PAL-NOT: .AMDGPU.config
 ; PAL-LABEL: {{^}}simple:
@@ -55,11 +56,13 @@ entry:
 ; Check code sequence for amdpal use of scratch for alloca in a compute shader.
 ; The scratch descriptor is loaded from offset 0x10 of the GIT, rather than offset
 ; 0 in a graphics shader.
+; Prior to GCN3 s_load_dword offsets are dwords, so the offset will be 0x4.
 
 ; PAL-LABEL: {{^}}scratch2_cs:
 ; PAL: s_movk_i32 s{{[0-9]+}}, 0x1234
 ; PAL: s_mov_b32 s[[GITPTR:[0-9]+]], s0
-; PAL: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:{{[0-9]+\]}}, 0x10
+; CI: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:{{[0-9]+\]}}, 0x4
+; VI: s_load_dwordx4 s{{\[}}[[SCRATCHDESC:[0-9]+]]:{{[0-9]+]}}, s{{\[}}[[GITPTR]]:{{[0-9]+\]}}, 0x10
 ; PAL: buffer_store{{.*}}, s{{\[}}[[SCRATCHDESC]]:
 
 define amdgpu_cs void @scratch2_cs(i32 inreg, i32 inreg, i32 inreg, <3 x i32> inreg, i32 inreg, <3 x i32> %coord, <2 x i32> %in, i32 %extra, i32 %idx) #0 {