From 93df06087195fc0fbeb70f9366bb6d8b64821dcd Mon Sep 17 00:00:00 2001
From: Marek Olsak <marek.olsak@amd.com>
Date: Mon, 27 Jul 2015 18:16:08 +0000
Subject: [PATCH] AMDGPU: don't match vgpr loads for constant loads

Author: Dave Airlie <airlied@redhat.com>

In order to implement indirect sampler loads, we don't
want to match on a VGPR load but an SGPR one for constants,
as we cannot feed VGPRs to the sampler only SGPRs.

this should be applicable for llvm 3.7 as well.

llvm-svn: 243294
---
 llvm/lib/Target/AMDGPU/SIInstructions.td       |  3 ---
 llvm/test/CodeGen/AMDGPU/gv-const-addrspace.ll | 12 +++---------
 llvm/test/CodeGen/AMDGPU/smrd.ll               |  8 +-------
 3 files changed, 4 insertions(+), 19 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/SIInstructions.td b/llvm/lib/Target/AMDGPU/SIInstructions.td
index b2edc03..c296aeb 100644
--- a/llvm/lib/Target/AMDGPU/SIInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -2910,9 +2910,6 @@ defm : MUBUFLoad_Pattern <BUFFER_LOAD_SBYTE_ADDR64, i32, sextloadi8_constant>;
 defm : MUBUFLoad_Pattern <BUFFER_LOAD_UBYTE_ADDR64, i32, az_extloadi8_constant>;
 defm : MUBUFLoad_Pattern <BUFFER_LOAD_SSHORT_ADDR64, i32, sextloadi16_constant>;
 defm : MUBUFLoad_Pattern <BUFFER_LOAD_USHORT_ADDR64, i32, az_extloadi16_constant>;
-defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORD_ADDR64, i32, constant_load>;
-defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORDX2_ADDR64, v2i32, constant_load>;
-defm : MUBUFLoad_Pattern <BUFFER_LOAD_DWORDX4_ADDR64, v4i32, constant_load>;
 } // End Predicates = [isSICI]
 
 class MUBUFScratchLoadPat <MUBUF Instr, ValueType vt, PatFrag ld> : Pat <
diff --git a/llvm/test/CodeGen/AMDGPU/gv-const-addrspace.ll b/llvm/test/CodeGen/AMDGPU/gv-const-addrspace.ll
index 3c1fc6c..d4d1312 100644
--- a/llvm/test/CodeGen/AMDGPU/gv-const-addrspace.ll
+++ b/llvm/test/CodeGen/AMDGPU/gv-const-addrspace.ll
@@ -8,9 +8,7 @@
 @float_gv = internal unnamed_addr addrspace(2) constant [5 x float] [float 0.0, float 1.0, float 2.0, float 3.0, float 4.0], align 4
 
 ; FUNC-LABEL: {{^}}float:
-; FIXME: We should be using s_load_dword here.
-; SI: buffer_load_dword
-; VI: s_load_dword
+; GCN: s_load_dword
 
 ; EG-DAG: MOV {{\** *}}T2.X
 ; EG-DAG: MOV {{\** *}}T3.X
@@ -31,9 +29,7 @@ entry:
 
 ; FUNC-LABEL: {{^}}i32:
 
-; FIXME: We should be using s_load_dword here.
-; SI: buffer_load_dword
-; VI: s_load_dword
+; GCN: s_load_dword
 
 ; EG-DAG: MOV {{\** *}}T2.X
 ; EG-DAG: MOV {{\** *}}T3.X
@@ -71,9 +67,7 @@ define void @struct_foo_gv_load(i32 addrspace(1)* %out, i32 %index) {
                                                                 <1 x i32> <i32 4> ]
 
 ; FUNC-LABEL: {{^}}array_v1_gv_load:
-; FIXME: We should be using s_load_dword here.
-; SI: buffer_load_dword
-; VI: s_load_dword
+; GCN: s_load_dword
 define void @array_v1_gv_load(<1 x i32> addrspace(1)* %out, i32 %index) {
   %gep = getelementptr inbounds [4 x <1 x i32>], [4 x <1 x i32>] addrspace(2)* @array_v1_gv, i32 0, i32 %index
   %load = load <1 x i32>, <1 x i32> addrspace(2)* %gep, align 4
diff --git a/llvm/test/CodeGen/AMDGPU/smrd.ll b/llvm/test/CodeGen/AMDGPU/smrd.ll
index b0c18ca..0598208 100644
--- a/llvm/test/CodeGen/AMDGPU/smrd.ll
+++ b/llvm/test/CodeGen/AMDGPU/smrd.ll
@@ -43,13 +43,7 @@ entry:
 ; GCN-LABEL: {{^}}smrd3:
 ; FIXME: There are too many copies here because we don't fold immediates
 ;        through REG_SEQUENCE
-; SI: s_mov_b32 s[[SLO:[0-9]+]], 0 ;
-; SI: s_mov_b32 s[[SHI:[0-9]+]], 4
-; SI: s_mov_b32 s[[SSLO:[0-9]+]], s[[SLO]]
-; SI-DAG: v_mov_b32_e32 v[[VLO:[0-9]+]], s[[SSLO]]
-; SI-DAG: v_mov_b32_e32 v[[VHI:[0-9]+]], s[[SHI]]
-; FIXME: We should be able to use s_load_dword here
-; SI: buffer_load_dword v{{[0-9]+}}, v{{\[}}[[VLO]]:[[VHI]]{{\]}}, s[{{[0-9]+:[0-9]+}}], 0 addr64
+; SI: s_load_dwordx2 s[{{[0-9]:[0-9]}}], s[{{[0-9]:[0-9]}}], 0xb ; encoding: [0x0b
 ; TODO: Add VI checks
 ; GCN: s_endpgm
 define void @smrd3(i32 addrspace(1)* %out, i32 addrspace(2)* %ptr) {
-- 
2.7.4