AMDGPU/GCN: Bring processors in sync with AMDGPUUsage

[kzhuravl]

Summary

• Add gfx704
  • Change bonaire to gfx704
• Remove gfx804
• Remove gfx901
• Remove gfx903

[t-tye]

LGTM except Bonaire changes.

lib/Target/AMDGPU/AMDGPU.td

536–540

D40051 proposes making Bonaire separate from Kaveri and named gfx704.

lib/Target/AMDGPU/GCNProcessors.td

83–91

D40051 proposes making Bonaire separate from Kaveri and named gfx704.

lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

123

D40051 proposes making Bonaire separate from Kaveri and named gfx704.

[kzhuravl]

Change bonaire to gfx704

[kzhuravl]

Ping

lib/Target/AMDGPU/AMDGPU.td

 
 def FeatureISAVersion7_0_2 : SubtargetFeatureISAVersion <7,0,2,
   [FeatureSeaIslands,
    FeatureLDSBankCount16]>;
 
 def FeatureISAVersion7_0_3 : SubtargetFeatureISAVersion <7,0,3,
   [FeatureSeaIslands,
    FeatureLDSBankCount16]>;
 
+def FeatureISAVersion7_0_4 : SubtargetFeatureISAVersion <7,0,4,
+  [FeatureSeaIslands,
+   FeatureLDSBankCount32]>;
+
 def FeatureISAVersion8_0_0 : SubtargetFeatureISAVersion <8,0,0,
   [FeatureVolcanicIslands,
    FeatureLDSBankCount32,
    FeatureSGPRInitBug]>;
 
 def FeatureISAVersion8_0_1 : SubtargetFeatureISAVersion <8,0,1,
   [FeatureVolcanicIslands,
    FeatureFastFMAF32,
    HalfRate64Ops,
    FeatureLDSBankCount32,
    FeatureXNACK]>;
 
 def FeatureISAVersion8_0_2 : SubtargetFeatureISAVersion <8,0,2,
   [FeatureVolcanicIslands,
    FeatureLDSBankCount32,
    FeatureSGPRInitBug]>;
 
 def FeatureISAVersion8_0_3 : SubtargetFeatureISAVersion <8,0,3,
   [FeatureVolcanicIslands,
    FeatureLDSBankCount32]>;
 
-def FeatureISAVersion8_0_4 : SubtargetFeatureISAVersion <8,0,4,
-  [FeatureVolcanicIslands,
-   FeatureLDSBankCount32]>;
-
 def FeatureISAVersion8_1_0 : SubtargetFeatureISAVersion <8,1,0,
   [FeatureVolcanicIslands,
    FeatureLDSBankCount16,
    FeatureXNACK]>;
 
 def FeatureISAVersion9_0_0 : SubtargetFeatureISAVersion <9,0,0,
   [FeatureGFX9,
    FeatureMadMixInsts,
    FeatureLDSBankCount32
    ]>;
 
-def FeatureISAVersion9_0_1 : SubtargetFeatureISAVersion <9,0,1,
-  [FeatureGFX9,
-   FeatureMadMixInsts,
-   FeatureLDSBankCount32,
-   FeatureXNACK]>;
-
 def FeatureISAVersion9_0_2 : SubtargetFeatureISAVersion <9,0,2,
   [FeatureGFX9,
    FeatureMadMixInsts,
    FeatureLDSBankCount32
    ]>;
 
-def FeatureISAVersion9_0_3 : SubtargetFeatureISAVersion <9,0,3,
-  [FeatureGFX9,
-   FeatureMadMixInsts,
-   FeatureLDSBankCount32,
-   FeatureXNACK]>;
-
 //===----------------------------------------------------------------------===//
 // Debugger related subtarget features.
 //===----------------------------------------------------------------------===//
 
 def FeatureDebuggerInsertNops : SubtargetFeature<
   "amdgpu-debugger-insert-nops",
   "DebuggerInsertNops",
   "true",

lib/Target/AMDGPU/AMDGPUSubtarget.h

public:
   enum {
     ISAVersion0_0_0,
     ISAVersion6_0_0,
     ISAVersion6_0_1,
     ISAVersion7_0_0,
     ISAVersion7_0_1,
     ISAVersion7_0_2,
     ISAVersion7_0_3,
+    ISAVersion7_0_4,
     ISAVersion8_0_0,
     ISAVersion8_0_1,
     ISAVersion8_0_2,
     ISAVersion8_0_3,
-    ISAVersion8_0_4,
     ISAVersion8_1_0,
     ISAVersion9_0_0,
-    ISAVersion9_0_1,
-    ISAVersion9_0_2,
-    ISAVersion9_0_3
+    ISAVersion9_0_2
   };
 
   enum TrapHandlerAbi {
     TrapHandlerAbiNone = 0,
     TrapHandlerAbiHsa = 1
   };
 
   enum TrapID {

lib/Target/AMDGPU/GCNProcessors.td

 //===----------------------------------------------------------------------===//
 // GCN GFX7 (Sea Islands (CI)).
 //===----------------------------------------------------------------------===//
 
 def : ProcessorModel<"gfx700", SIQuarterSpeedModel,
   [FeatureISAVersion7_0_0]
 >;
 
-def : ProcessorModel<"bonaire", SIQuarterSpeedModel,
-  [FeatureISAVersion7_0_0]
->;
-
 def : ProcessorModel<"kaveri", SIQuarterSpeedModel,
   [FeatureISAVersion7_0_0]
 >;
 
 def : ProcessorModel<"gfx701", SIFullSpeedModel,
   [FeatureISAVersion7_0_1]
 >;
 

 
 def : ProcessorModel<"kabini", SIQuarterSpeedModel,
   [FeatureISAVersion7_0_3]
 >;
 
 def : ProcessorModel<"mullins", SIQuarterSpeedModel,
   [FeatureISAVersion7_0_3]
 >;
 
+def : ProcessorModel<"gfx704", SIQuarterSpeedModel,
+  [FeatureISAVersion7_0_4]
+>;
+
+def : ProcessorModel<"bonaire", SIQuarterSpeedModel,
+  [FeatureISAVersion7_0_4]
+>;
+
 //===----------------------------------------------------------------------===//
 // GCN GFX8 (Volcanic Islands (VI)).
 //===----------------------------------------------------------------------===//
 
 def : ProcessorModel<"gfx800", SIQuarterSpeedModel,
   [FeatureISAVersion8_0_0]
 >;
 

 def : ProcessorModel<"polaris10", SIQuarterSpeedModel,
   [FeatureISAVersion8_0_3]
 >;
 
 def : ProcessorModel<"polaris11", SIQuarterSpeedModel,
   [FeatureISAVersion8_0_3]
 >;
 
-def : ProcessorModel<"gfx804", SIQuarterSpeedModel,
-  [FeatureISAVersion8_0_4]
->;
-
 def : ProcessorModel<"gfx810", SIQuarterSpeedModel,
   [FeatureISAVersion8_1_0]
 >;
 
 def : ProcessorModel<"stoney", SIQuarterSpeedModel,
   [FeatureISAVersion8_1_0]
 >;
 
 //===----------------------------------------------------------------------===//
 // GCN GFX9.
 //===----------------------------------------------------------------------===//
 
 def : ProcessorModel<"gfx900", SIQuarterSpeedModel,
   [FeatureISAVersion9_0_0]
 >;
 
-def : ProcessorModel<"gfx901", SIQuarterSpeedModel,
-  [FeatureISAVersion9_0_1]
->;
-
 def : ProcessorModel<"gfx902", SIQuarterSpeedModel,
   [FeatureISAVersion9_0_2]
 >;
-
-def : ProcessorModel<"gfx903", SIQuarterSpeedModel,
-  [FeatureISAVersion9_0_3]
->;

lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

static cl::opt<bool> EnablePackedInlinableLiterals(
     cl::desc("Enable packed inlinable literals (v2f16, v2i16)"),
     cl::init(false));
 
 namespace AMDGPU {
 
 namespace IsaInfo {
 
 IsaVersion getIsaVersion(const FeatureBitset &Features) {
-  // SI.
+  // GCN GFX6 (Southern Islands (SI)).
   if (Features.test(FeatureISAVersion6_0_0))
     return {6, 0, 0};
   if (Features.test(FeatureISAVersion6_0_1))
     return {6, 0, 1};
-  // CI.
+
+  // GCN GFX7 (Sea Islands (CI)).
   if (Features.test(FeatureISAVersion7_0_0))
     return {7, 0, 0};
   if (Features.test(FeatureISAVersion7_0_1))
     return {7, 0, 1};
   if (Features.test(FeatureISAVersion7_0_2))
     return {7, 0, 2};
   if (Features.test(FeatureISAVersion7_0_3))
     return {7, 0, 3};
+  if (Features.test(FeatureISAVersion7_0_4))
+    return {7, 0, 4};
 
-  // VI.
+  // GCN GFX8 (Volcanic Islands (VI)).
   if (Features.test(FeatureISAVersion8_0_0))
     return {8, 0, 0};
   if (Features.test(FeatureISAVersion8_0_1))
     return {8, 0, 1};
   if (Features.test(FeatureISAVersion8_0_2))
     return {8, 0, 2};
   if (Features.test(FeatureISAVersion8_0_3))
     return {8, 0, 3};
-  if (Features.test(FeatureISAVersion8_0_4))
-    return {8, 0, 4};
   if (Features.test(FeatureISAVersion8_1_0))
     return {8, 1, 0};
 
-  // GFX9.
+  // GCN GFX9.
   if (Features.test(FeatureISAVersion9_0_0))
     return {9, 0, 0};
-  if (Features.test(FeatureISAVersion9_0_1))
-    return {9, 0, 1};
   if (Features.test(FeatureISAVersion9_0_2))
     return {9, 0, 2};
-  if (Features.test(FeatureISAVersion9_0_3))
-    return {9, 0, 3};
 
   if (!Features.test(FeatureGCN) || Features.test(FeatureSouthernIslands))
     return {0, 0, 0};
   return {7, 0, 0};
 }
 
 void streamIsaVersion(const MCSubtargetInfo *STI, raw_ostream &Stream) {
   auto TargetTriple = STI->getTargetTriple();

test/CodeGen/AMDGPU/add.v2i16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
 
 ; FIXME: Need to handle non-uniform case for function below (load without gep).
 ; GCN-LABEL: {{^}}v_test_add_v2i16:
 ; GFX9: v_pk_add_u16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 
 ; VI: v_add_u16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 ; VI: v_add_u16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}

test/CodeGen/AMDGPU/ashr.v2i16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=CIVI %s
 ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=CIVI %s
 
 ; GCN-LABEL: {{^}}s_ashr_v2i16:
 ; GFX9: s_load_dword [[LHS:s[0-9]+]]
 ; GFX9: s_load_dword [[RHS:s[0-9]+]]
 ; GFX9: v_mov_b32_e32 [[VLHS:v[0-9]+]], [[LHS]]
 ; GFX9: v_pk_ashrrev_i16 [[RESULT:v[0-9]+]], [[RHS]], [[VLHS]]

test/CodeGen/AMDGPU/extract_vector_elt-i16.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SICIVI %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=SICIVI %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 
 ; GCN-LABEL: {{^}}extract_vector_elt_v2i16:
 ; GCN: s_load_dword [[VEC:s[0-9]+]]
 ; GCN: s_lshr_b32 [[ELT1:s[0-9]+]], [[VEC]], 16
 ; GCN-DAG: v_mov_b32_e32 [[VELT0:v[0-9]+]], [[VEC]]
 ; GCN-DAG: v_mov_b32_e32 [[VELT1:v[0-9]+]], [[ELT1]]
 ; GCN-DAG: buffer_store_short [[VELT0]]
 ; GCN-DAG: buffer_store_short [[VELT1]]

test/CodeGen/AMDGPU/fabs.f16.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=CI %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
 
 ; DAGCombiner will transform:
 ; (fabs (f16 bitcast (i16 a))) => (f16 bitcast (and (i16 a), 0x7FFFFFFF))
 ; unless isFabsFree returns true
 
 ; GCN-LABEL: {{^}}s_fabs_free_f16:
 ; GCN: {{flat|global}}_load_ushort [[VAL:v[0-9]+]],
 ; GCN: v_and_b32_e32 [[RESULT:v[0-9]+]], 0x7fff, [[VAL]]

test/CodeGen/AMDGPU/fcanonicalize-elimination.ll

 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -mattr=-fp32-denormals < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,GCN-FLUSH %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs -mattr=-fp32-denormals,+fp-exceptions < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN-EXCEPT,VI,GCN-FLUSH %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs -mattr=+fp32-denormals < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX9-DENORM,GCN-DENORM %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs -mattr=-fp32-denormals < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX9-FLUSH,GCN-FLUSH %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -mattr=+fp32-denormals < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX9-DENORM,GCN-DENORM %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -mattr=-fp32-denormals < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,GFX9-FLUSH,GCN-FLUSH %s
 
 ; GCN-LABEL: {{^}}test_no_fold_canonicalize_loaded_value_f32:
 ; GCN-FLUSH:   v_mul_f32_e32 v{{[0-9]+}}, 1.0, v{{[0-9]+}}
 ; GFX9-DENORM: v_max_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 define amdgpu_kernel void @test_no_fold_canonicalize_loaded_value_f32(float addrspace(1)* %arg) {
   %id = tail call i32 @llvm.amdgcn.workitem.id.x()
   %gep = getelementptr inbounds float, float addrspace(1)* %arg, i32 %id
   %v = load float, float addrspace(1)* %gep, align 4

test/CodeGen/AMDGPU/fcanonicalize.f16.ll

 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 
 declare half @llvm.fabs.f16(half) #0
 declare half @llvm.canonicalize.f16(half) #0
 declare <2 x half> @llvm.fabs.v2f16(<2 x half>) #0
 declare <2 x half> @llvm.canonicalize.v2f16(<2 x half>) #0
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 
 

test/CodeGen/AMDGPU/fcopysign.f16.ll

 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX8 %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
 
 declare half @llvm.copysign.f16(half, half)
 declare float @llvm.copysign.f32(float, float)
 declare double @llvm.copysign.f64(double, double)
 declare <2 x half> @llvm.copysign.v2f16(<2 x half>, <2 x half>)
 declare <3 x half> @llvm.copysign.v3f16(<3 x half>, <3 x half>)
 declare <4 x half> @llvm.copysign.v4f16(<4 x half>, <4 x half>)
 

test/CodeGen/AMDGPU/fmed3.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=NOSNAN -check-prefix=GCN -check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mattr=+fp-exceptions -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=SNAN -check-prefix=GCN -check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=NOSNAN -check-prefix=GCN -check-prefix=VI -check-prefix=GFX89 %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=+fp-exceptions -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=SNAN -check-prefix=GCN -check-prefix=VI -check-prefix=GFX89 %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=NOSNAN -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=+fp-exceptions -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=SNAN -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=NOSNAN -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=+fp-exceptions -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=SNAN -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
 
 
 ; GCN-LABEL: {{^}}v_test_nnan_input_fmed3_r_i_i_f32:
 ; GCN: v_add_f32_e32 [[ADD:v[0-9]+]], 1.0, v{{[0-9]+}}
 ; GCN: v_med3_f32 v{{[0-9]+}}, [[ADD]], 2.0, 4.0
 define amdgpu_kernel void @v_test_nnan_input_fmed3_r_i_i_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr float, float addrspace(1)* %aptr, i32 %tid

test/CodeGen/AMDGPU/fmuladd.v2f16.ll

-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=-fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-FLUSH,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=-fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-FLUSH,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=-fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-FLUSH,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=-fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-FLUSH,GFX9 %s
-
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=+fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-DENORM-STRICT,GFX9-DENORM,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=+fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-DENORM-STRICT,GFX9-DENORM,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=+fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-DENORM-CONTRACT,GFX9-DENORM,GFX9 %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=+fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-DENORM-CONTRACT,GFX9-DENORM,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=-fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-FLUSH,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=-fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-FLUSH,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=-fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-FLUSH,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=-fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-FLUSH,GFX9 %s
+
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=+fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-DENORM-STRICT,GFX9-DENORM,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=+fp64-fp16-denormals -fp-contract=on -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-STRICT,GFX9-DENORM-STRICT,GFX9-DENORM,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=+fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-DENORM-CONTRACT,GFX9-DENORM,GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=+fp64-fp16-denormals -fp-contract=fast -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefixes=GCN,GCN-CONTRACT,GFX9-DENORM-CONTRACT,GFX9-DENORM,GFX9 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 declare <2 x half> @llvm.fmuladd.v2f16(<2 x half>, <2 x half>, <2 x half>) #1
 declare <2 x half> @llvm.fabs.v2f16(<2 x half>) #1
 
 ; GCN-LABEL: {{^}}fmuladd_v2f16:
 ; GFX9-FLUSH: v_pk_mul_f16 {{v[0-9]+, v[0-9]+, v[0-9]+}}
 ; GFX9-FLUSH: v_pk_add_f16 {{v[0-9]+, v[0-9]+, v[0-9]+}}

test/CodeGen/AMDGPU/fneg-fabs.f16.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=GCN -check-prefix=CIVI %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GFX89 -check-prefix=GCN -check-prefix=CIVI %s
-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx901 -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX89 -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX89 -check-prefix=GFX9 -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}fneg_fabs_fadd_f16:
 ; CI: v_cvt_f32_f16_e32
 ; CI: v_cvt_f32_f16_e64 [[CVT_ABS_X:v[0-9]+]], |v{{[0-9]+}}|
 ; CI: v_sub_f32_e32 v{{[0-9]+}}, v{{[0-9]+}}, [[CVT_ABS_X]]
 
 ; GFX89-NOT: _and
 ; GFX89: v_sub_f16_e64 {{v[0-9]+}}, {{v[0-9]+}}, |{{v[0-9]+}}|

test/CodeGen/AMDGPU/fneg.f16.ll

 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=kaveri -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,CIVI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,CIVI,GFX89 %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx901 -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX89,GFX9 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX89,GFX9 %s
 
 ; FIXME: Should be able to do scalar op
 ; GCN-LABEL: {{^}}s_fneg_f16:
 define amdgpu_kernel void @s_fneg_f16(half addrspace(1)* %out, half %in) #0 {
   %fneg = fsub half -0.0, %in
   store half %fneg, half addrspace(1)* %out
   ret void
 }

test/CodeGen/AMDGPU/fpext.f16.ll

 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=SIVI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=GFX89 %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 %s
 
 ; GCN-LABEL: {{^}}fpext_f16_to_f32
 ; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
 ; GCN: v_cvt_f32_f16_e32 v[[R_F32:[0-9]+]], v[[A_F16]]
 ; GCN: buffer_store_dword v[[R_F32]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @fpext_f16_to_f32(
     float addrspace(1)* %r,

test/CodeGen/AMDGPU/fptrunc.f16.ll

 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=SIVI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=SIVI %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs -enable-unsafe-fp-math < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
 
 ; GCN-LABEL: {{^}}fptrunc_f32_to_f16:
 ; GCN: buffer_load_dword v[[A_F32:[0-9]+]]
 ; GCN: v_cvt_f16_f32_e32 v[[R_F16:[0-9]+]], v[[A_F32]]
 ; GCN: buffer_store_short v[[R_F16]]
 ; GCN: s_endpgm
 define amdgpu_kernel void @fptrunc_f32_to_f16(
     half addrspace(1)* %r,

test/CodeGen/AMDGPU/fsub.f16.ll

 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SIVI %s
 ; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=VI -check-prefix=SIVI %s
-; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
 
 ; GCN-LABEL: {{^}}fsub_f16:
 ; GCN: buffer_load_ushort v[[A_F16:[0-9]+]]
 ; GCN: buffer_load_ushort v[[B_F16:[0-9]+]]
 ; SI:  v_cvt_f32_f16_e32 v[[A_F32:[0-9]+]], v[[A_F16]]
 ; SI:  v_cvt_f32_f16_e32 v[[B_F32:[0-9]+]], v[[B_F16]]
 ; SI:  v_sub_f32_e32 v[[R_F32:[0-9]+]], v[[A_F32]], v[[B_F32]]
 ; SI:  v_cvt_f16_f32_e32 v[[R_F16:[0-9]+]], v[[R_F32]]

test/CodeGen/AMDGPU/hsa-note-no-func.ll

 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx600 | FileCheck --check-prefix=HSA --check-prefix=HSA-SI600 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx601 | FileCheck --check-prefix=HSA --check-prefix=HSA-SI601 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx700 | FileCheck --check-prefix=HSA --check-prefix=HSA-CI700 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx701 | FileCheck --check-prefix=HSA --check-prefix=HSA-CI701 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx702 | FileCheck --check-prefix=HSA --check-prefix=HSA-CI702 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx703 | FileCheck --check-prefix=HSA --check-prefix=HSA-CI703 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx704 | FileCheck --check-prefix=HSA --check-prefix=HSA-CI704 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=bonaire | FileCheck --check-prefix=HSA --check-prefix=HSA-CI704 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=mullins | FileCheck --check-prefix=HSA --check-prefix=HSA-CI703 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=hawaii | FileCheck --check-prefix=HSA --check-prefix=HSA-CI701 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kabini | FileCheck --check-prefix=HSA --check-prefix=HSA-CI703 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefix=HSA --check-prefix=HSA-CI700 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-flat-for-global | FileCheck --check-prefix=HSA --check-prefix=HSA-VI801 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=tonga -mattr=-flat-for-global | FileCheck --check-prefix=HSA --check-prefix=HSA-VI802 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global | FileCheck --check-prefix=HSA --check-prefix=HSA-VI803 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris10 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI803 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris11 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI803 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx800 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI800 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx801 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI801 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx802 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI802 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx803 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI803 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx804 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI804 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx810 | FileCheck --check-prefix=HSA --check-prefix=HSA-VI810 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx900 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX900 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx901 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX901 %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx902 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX902 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx903 | FileCheck --check-prefix=HSA --check-prefix=HSA-GFX903 %s
 
 ; HSA: .hsa_code_object_version 2,1
 ; HSA-SI600: .hsa_code_object_isa 6,0,0,"AMD","AMDGPU"
 ; HSA-SI601: .hsa_code_object_isa 6,0,1,"AMD","AMDGPU"
 ; HSA-CI700: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 ; HSA-CI701: .hsa_code_object_isa 7,0,1,"AMD","AMDGPU"
 ; HSA-CI702: .hsa_code_object_isa 7,0,2,"AMD","AMDGPU"
 ; HSA-CI703: .hsa_code_object_isa 7,0,3,"AMD","AMDGPU"
+; HSA-CI704: .hsa_code_object_isa 7,0,4,"AMD","AMDGPU"
 ; HSA-VI800: .hsa_code_object_isa 8,0,0,"AMD","AMDGPU"
 ; HSA-VI801: .hsa_code_object_isa 8,0,1,"AMD","AMDGPU"
 ; HSA-VI802: .hsa_code_object_isa 8,0,2,"AMD","AMDGPU"
 ; HSA-VI803: .hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
-; HSA-VI804: .hsa_code_object_isa 8,0,4,"AMD","AMDGPU"
 ; HSA-VI810: .hsa_code_object_isa 8,1,0,"AMD","AMDGPU"
 ; HSA-GFX900: .hsa_code_object_isa 9,0,0,"AMD","AMDGPU"
-; HSA-GFX901: .hsa_code_object_isa 9,0,1,"AMD","AMDGPU"
 ; HSA-GFX902: .hsa_code_object_isa 9,0,2,"AMD","AMDGPU"
-; HSA-GFX903: .hsa_code_object_isa 9,0,3,"AMD","AMDGPU"

test/CodeGen/AMDGPU/immv216.ll

-; RUN:  llc -amdgpu-scalarize-global-loads=false  -mtriple=amdgcn--amdhsa -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI %s
 ; FIXME: Merge into imm.ll
 
 ; GCN-LABEL: {{^}}store_inline_imm_neg_0.0_v2i16:
 ; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 0x80008000{{$}}
 ; GCN: buffer_store_dword [[REG]]
 define amdgpu_kernel void @store_inline_imm_neg_0.0_v2i16(<2 x i16> addrspace(1)* %out) #0 {

test/CodeGen/AMDGPU/inlineasm-packed.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}inline_asm_input_v2i16:
 ; GCN: s_mov_b32 s{{[0-9]+}}, s{{[0-9]+}}
 define amdgpu_kernel void @inline_asm_input_v2i16(i32 addrspace(1)* %out, <2 x i16> %in) #0 {
 entry:
   %val = call i32 asm "s_mov_b32 $0, $1", "=r,r"(<2 x i16> %in) #0
   store i32 %val, i32 addrspace(1)* %out
   ret void

test/CodeGen/AMDGPU/llvm.amdgcn.cvt.pkrtz.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX89 -check-prefix=GFX9 %s
 
 ; GCN-LABEL: {{^}}s_cvt_pkrtz_v2f16_f32:
 ; GCN-DAG: s_load_dword [[X:s[0-9]+]], s[0:1], 0x{{b|2c}}
 ; GCN-DAG: s_load_dword [[SY:s[0-9]+]], s[0:1], 0x{{c|30}}
 ; GCN: v_mov_b32_e32 [[VY:v[0-9]+]], [[SY]]
 ; SI: v_cvt_pkrtz_f16_f32_e32 v{{[0-9]+}}, [[X]], [[VY]]
 ; GFX89: v_cvt_pkrtz_f16_f32 v{{[0-9]+}}, [[X]], [[VY]]
 define amdgpu_kernel void @s_cvt_pkrtz_v2f16_f32(<2 x half> addrspace(1)* %out, float %x, float %y) #0 {

test/CodeGen/AMDGPU/llvm.amdgcn.exp.compr.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=GCN %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=GCN %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -strict-whitespace -check-prefix=GCN %s
 
 declare void @llvm.amdgcn.exp.compr.v2f16(i32, i32, <2 x half>, <2 x half>, i1, i1) #0
 declare void @llvm.amdgcn.exp.compr.v2i16(i32, i32, <2 x i16>, <2 x i16>, i1, i1) #0
 
 ; GCN-LABEL: {{^}}test_export_compr_zeroes_v2f16:
 ; GCN: exp mrt0 off, off, off, off compr{{$}}
 ; GCN: exp mrt0 off, off, off, off done compr{{$}}
 define amdgpu_kernel void @test_export_compr_zeroes_v2f16() #0 {

test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.f16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}test_fmed3_f16:
 ; GCN: v_med3_f16 v{{[0-9]+}}, s{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 define amdgpu_kernel void @test_fmed3_f16(half addrspace(1)* %out, i32 %src0.arg, i32 %src1.arg, i32 %src2.arg) #1 {
   %src0.f16 = trunc i32 %src0.arg to i16
   %src0 = bitcast i16 %src0.f16 to half
   %src1.f16 = trunc i32 %src1.arg to i16
   %src1 = bitcast i16 %src1.f16 to half

test/CodeGen/AMDGPU/lshr.v2i16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=CIVI %s
 ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=CIVI %s
 
 ; GCN-LABEL: {{^}}s_lshr_v2i16:
 ; GFX9: s_load_dword [[LHS:s[0-9]+]]
 ; GFX9: s_load_dword [[RHS:s[0-9]+]]
 ; GFX9: v_mov_b32_e32 [[VLHS:v[0-9]+]], [[LHS]]
 ; GFX9: v_pk_lshrrev_b16 [[RESULT:v[0-9]+]], [[RHS]], [[VLHS]]

test/CodeGen/AMDGPU/max.i16.ll

 ; RUN: llc -march=amdgcn -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=VIPLUS %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=VIPLUS %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=VIPLUS %s
 
 ; FIXME: Need to handle non-uniform case for function below (load without gep).
 ; GCN-LABEL: {{^}}v_test_imax_sge_i16:
 ; VIPLUS: v_max_i16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 define amdgpu_kernel void @v_test_imax_sge_i16(i16 addrspace(1)* %out, i16 addrspace(1)* %aptr, i16 addrspace(1)* %bptr) nounwind {
   %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone
   %gep0 = getelementptr i16, i16 addrspace(1)* %aptr, i32 %tid
   %gep1 = getelementptr i16, i16 addrspace(1)* %bptr, i32 %tid

test/CodeGen/AMDGPU/min.ll

 ; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=GFX89 -check-prefix=FUNC %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 -check-prefix=FUNC %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 -check-prefix=FUNC %s
 ; RUN: llc -march=r600 -mtriple=r600---amdgiz -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
 
 ; FUNC-LABEL: {{^}}v_test_imin_sle_i32:
 ; GCN: v_min_i32_e32
 
 ; EG: MIN_INT
 define amdgpu_kernel void @v_test_imin_sle_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %a.ptr, i32 addrspace(1)* %b.ptr) #0 {
   %tid = call i32 @llvm.r600.read.tidig.x()

test/CodeGen/AMDGPU/pack.v2f16.ll

-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx901 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI %s
 
 
 ; GCN-LABEL: {{^}}s_pack_v2f16:
 ; GFX9: s_load_dword [[VAL0:s[0-9]+]]
 ; GFX9: s_load_dword [[VAL1:s[0-9]+]]
 ; GFX9: s_pack_ll_b32_b16 [[PACKED:s[0-9]+]], [[VAL0]], [[VAL1]]

test/CodeGen/AMDGPU/pack.v2i16.ll

-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx901 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=-flat-for-global,-fp64-fp16-denormals -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=CI %s
 
 
 ; GCN-LABEL: {{^}}s_pack_v2i16:
 ; GFX9: s_load_dword [[VAL0:s[0-9]+]]
 ; GFX9: s_load_dword [[VAL1:s[0-9]+]]
 ; GFX9: s_pack_ll_b32_b16 [[PACKED:s[0-9]+]], [[VAL0]], [[VAL1]]

test/CodeGen/AMDGPU/scratch-simple.ll

 ; RUN: llc -march=amdgcn -mcpu=verde -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
-; RUN: llc -march=amdgcn -mcpu=gfx804 -mattr=-flat-for-global -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
+; RUN: llc -march=amdgcn -mcpu=gfx803 -mattr=-flat-for-global -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=GFX9 %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
 ;
 ; GCN-LABEL: {{^}}ps_main:
 

test/CodeGen/AMDGPU/sext-in-reg.ll

 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mtriple=amdgcn---amdgiz -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=SI -check-prefix=FUNC %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=VI -check-prefix=GFX89 -check-prefix=FUNC %s
-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 -check-prefix=FUNC %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 -check-prefix=GFX89 -check-prefix=FUNC %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=r600 -mtriple=r600---amdgiz -mcpu=cypress < %s | FileCheck -enable-var-scope -check-prefix=EG -check-prefix=FUNC %s
 
 ; FIXME: i16 promotion pass ruins the scalar cases when legal.
 ; FIXME: r600 fails verifier
 
 ; FUNC-LABEL: {{^}}sext_in_reg_i1_i32:
 ; GCN: s_load_dword [[ARG:s[0-9]+]],
 ; GCN: s_bfe_i32 [[SEXTRACT:s[0-9]+]], [[ARG]], 0x10000

test/CodeGen/AMDGPU/shl.v2i16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=CIVI %s
 ; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=CIVI %s
 
 ; GCN-LABEL: {{^}}s_shl_v2i16:
 ; GFX9: s_load_dword [[LHS:s[0-9]+]]
 ; GFX9: s_load_dword [[RHS:s[0-9]+]]
 ; GFX9: v_mov_b32_e32 [[VLHS:v[0-9]+]], [[LHS]]
 ; GFX9: v_pk_lshlrev_b16 [[RESULT:v[0-9]+]], [[RHS]], [[VLHS]]

test/CodeGen/AMDGPU/smed3.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SICIVI -check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SICIVI -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 
 ; GCN-LABEL: {{^}}v_test_smed3_r_i_i_i32:
 ; GCN: v_med3_i32 v{{[0-9]+}}, v{{[0-9]+}}, 12, 17
 define amdgpu_kernel void @v_test_smed3_r_i_i_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid

test/CodeGen/AMDGPU/sminmax.v2i16.ll

-; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=CIVI -check-prefix=GCN %s
 ; RUN:  llc -amdgpu-scalarize-global-loads=false  -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=CIVI -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}s_abs_v2i16:
 ; GFX9: s_load_dword [[VAL:s[0-9]+]]
 ; GFX9: v_pk_sub_i16 [[SUB:v[0-9]+]], 0, [[VAL]]
 ; GFX9: v_pk_max_i16 [[MAX:v[0-9]+]], [[VAL]], [[SUB]]
 ; GFX9: v_pk_add_u16 [[ADD:v[0-9]+]], [[MAX]], 2

test/CodeGen/AMDGPU/sub.v2i16.ll

-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -enable-packed-inlinable-literals < %s | FileCheck -check-prefix=GFX9 -check-prefix=GCN %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
 
 ; FIXME: Need to handle non-uniform case for function below (load without gep).
 ; GCN-LABEL: {{^}}v_test_sub_v2i16:
 ; GFX9: v_pk_sub_i16 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
 
 ; VI: v_sub_u16_sdwa v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:DWORD
 ; VI: v_sub_u16_e32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}

test/CodeGen/AMDGPU/umed3.ll

 ; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SICIVI -check-prefix=SI %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SICIVI -check-prefix=VI %s
-; RUN: llc -march=amdgcn -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
+; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 
 ; GCN-LABEL: {{^}}v_test_umed3_r_i_i_i32:
 ; GCN: v_med3_u32 v{{[0-9]+}}, v{{[0-9]+}}, 12, 17
 define amdgpu_kernel void @v_test_umed3_r_i_i_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #1 {
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid

test/MC/AMDGPU/gfx9_asm_all.s

-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s | FileCheck %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck %s
 
 ds_add_u32 v1, v2 offset:65535
 // CHECK: [0xff,0xff,0x00,0xd8,0x01,0x02,0x00,0x00]
 
 ds_add_u32 v255, v2 offset:65535
 // CHECK: [0xff,0xff,0x00,0xd8,0xff,0x02,0x00,0x00]
 
 ds_add_u32 v1, v255 offset:65535

test/MC/AMDGPU/hsa_code_object_isa_args.s

 // RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_700
-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=gfx804 -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_804
+// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=gfx803 -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_803
 // RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=stoney -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_810
 // RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri -show-encoding %s | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF --check-prefix=ELF_700
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=gfx804 -show-encoding %s | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF --check-prefix=ELF_804
+// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=gfx803 -show-encoding %s | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF --check-prefix=ELF_803
 // RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=stoney -show-encoding %s | llvm-readobj -s -sd | FileCheck %s --check-prefix=ELF --check-prefix=ELF_810
 
 // ELF: SHT_NOTE
 // ELF: 0000: 04000000 08000000 01000000 414D4400
 // ELF: 0010: 01000000 00000000 04000000 1B000000
 // ELF_700: 0020: 03000000 414D4400 04000700 07000000
 // ELF_700: 0030: 00000000 00000000 414D4400 414D4447
-// ELF_804: 0020: 03000000 414D4400 04000700 08000000
-// ELF_804: 0030: 00000000 04000000 414D4400 414D4447
+// ELF_803: 0020: 03000000 414D4400 04000700 08000000
+// ELF_803: 0030: 00000000 03000000 414D4400 414D4447
 // ELF_810: 0020: 03000000 414D4400 04000700 08000000
 // ELF_810: 0030: 01000000 00000000 414D4400 414D4447
 // ELF: 0040: 50550000
 
 .hsa_code_object_version 1,0
 // ASM: .hsa_code_object_version 1,0
 
 // Test defaults
 .hsa_code_object_isa
 // ASM_700: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM_804: .hsa_code_object_isa 8,0,4,"AMD","AMDGPU"
+// ASM_803: .hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
 // ASM_810: .hsa_code_object_isa 8,1,0,"AMD","AMDGPU"
 
 // Test expressions and symbols
 .set A,2
 .hsa_code_object_isa A+1,A*2,A/A+4,"AMD","AMDGPU"
 // ASM: .hsa_code_object_isa 3,4,5,"AMD","AMDGPU"

test/MC/AMDGPU/literalv216.s

-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
 
 v_pk_add_f16 v1, 0, v2
 // GFX9: v_pk_add_f16 v1, 0, v2 ; encoding: [0x01,0x00,0x8f,0xd3,0x80,0x04,0x02,0x18]
 
 v_pk_add_f16 v1, 0.0, v2
 // GFX9: v_pk_add_f16 v1, 0, v2 ; encoding: [0x01,0x00,0x8f,0xd3,0x80,0x04,0x02,0x18]
 
 v_pk_add_f16 v1, v2, 0

test/MC/AMDGPU/sym_option.s

 // RUN: llvm-mc -arch=amdgcn -mcpu=tahiti      %s | FileCheck %s --check-prefix=SI
 // RUN: llvm-mc -arch=amdgcn -mcpu=bonaire %s | FileCheck %s --check-prefix=BONAIRE
 // RUN: llvm-mc -arch=amdgcn -mcpu=hawaii %s | FileCheck %s --check-prefix=HAWAII
 // RUN: llvm-mc -arch=amdgcn -mcpu=kabini  %s | FileCheck %s --check-prefix=KABINI
 // RUN: llvm-mc -arch=amdgcn -mcpu=iceland %s | FileCheck %s --check-prefix=ICELAND
 // RUN: llvm-mc -arch=amdgcn -mcpu=carrizo %s | FileCheck %s --check-prefix=CARRIZO
 // RUN: llvm-mc -arch=amdgcn -mcpu=tonga %s | FileCheck %s --check-prefix=TONGA
 // RUN: llvm-mc -arch=amdgcn -mcpu=fiji %s | FileCheck %s --check-prefix=FIJI
-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx804  %s | FileCheck %s --check-prefix=GFX804
 // RUN: llvm-mc -arch=amdgcn -mcpu=stoney  %s | FileCheck %s --check-prefix=STONEY
 
 .byte .option.machine_version_major
 // SI: .byte 6
 // BONAIRE: .byte 7
 // HAWAII: .byte 7
 // KABINI: .byte 7
 // ICELAND: .byte 8
 // CARRIZO: .byte 8
 // TONGA: .byte 8
 // FIJI: .byte 8
-// GFX804: .byte 8
 // STONEY: .byte 8
 
 .byte .option.machine_version_minor
 // SI: .byte 0
 // BONAIRE: .byte 0
 // HAWAII: .byte 0
 // KABINI: .byte 0
 // ICELAND: .byte 0
 // CARRIZO: .byte 0
 // TONGA: .byte 0
 // FIJI: .byte 0
-// GFX804: .byte 0
 // STONEY: .byte 1
 
 .byte .option.machine_version_stepping
 // SI: .byte 0
-// BONAIRE: .byte 0
+// BONAIRE: .byte 4
 // HAWAII: .byte 1
 // KABINI: .byte 3
 // ICELAND: .byte 0
 // CARRIZO: .byte 1
 // TONGA: .byte 2
 // FIJI: .byte 3
-// GFX804: .byte 4
 // STONEY: .byte 0

test/MC/AMDGPU/vop1-gfx9.s

-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=tahiti -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=hawaii -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=tonga -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 
 v_swap_b32 v1, v2
 // GFX9: v_swap_b32 v1, v2 ; encoding: [0x02,0xa3,0x02,0x7e]
 // NOVI: :1: error: instruction not supported on this GPU
 
 // FIXME: Error for it requiring VOP1 encoding
 v_swap_b32_e32 v1, v2
 // GFX9: v_swap_b32 v1, v2 ; encoding: [0x02,0xa3,0x02,0x7e]
 // NOVI: :1: error: instruction not supported on this GPU

test/MC/AMDGPU/vop3-gfx9.s

-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=tahiti -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=hawaii -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 // RUN: not llvm-mc -arch=amdgcn -mcpu=tonga -show-encoding %s 2>&1 | FileCheck -check-prefix=NOVI %s
 
 v_lshl_add_u32 v1, v2, v3, v4
 // GFX9: v_lshl_add_u32 v1, v2, v3, v4 ; encoding: [0x01,0x00,0xfd,0xd1,0x02,0x07,0x12,0x04]
 // NOVI: :1: error: instruction not supported on this GPU
 

test/MC/AMDGPU/vop3p-err.s

-// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s 2>&1 | FileCheck -check-prefix=GFX9 %s
+// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s 2>&1 | FileCheck -check-prefix=GFX9 %s
 
 // GFX9: 31: error: failed parsing operand.
 v_pk_add_u16 v1, v2, v3 op_sel
 
 // GFX9: 32: error: failed parsing operand.
 v_pk_add_u16 v1, v2, v3 op_sel:
 
 // GFX9: 33: error: failed parsing operand.

test/MC/AMDGPU/vop3p.s

-// RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
+// RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s | FileCheck -check-prefix=GFX9 %s
 
 //
 // Test op_sel/op_sel_hi
 //
 
 v_pk_add_u16 v1, v2, v3
 // GFX9: v_pk_add_u16 v1, v2, v3 ; encoding: [0x01,0x00,0x8a,0xd3,0x02,0x07,0x02,0x18]
 

test/MC/Disassembler/AMDGPU/gfx9_dasm_all.txt

-# RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -disassemble -show-encoding < %s | FileCheck %s
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -disassemble -show-encoding < %s | FileCheck %s
 
 # CHECK: ds_add_u32 v1, v2 offset:65535    ; encoding: [0xff,0xff,0x00,0xd8,0x01,0x02,0x00,0x00]
 0xff,0xff,0x00,0xd8,0x01,0x02,0x00,0x00
 
 # CHECK: ds_add_u32 v255, v2 offset:65535    ; encoding: [0xff,0xff,0x00,0xd8,0xff,0x02,0x00,0x00]
 0xff,0xff,0x00,0xd8,0xff,0x02,0x00,0x00
 
 # CHECK: ds_add_u32 v1, v255 offset:65535    ; encoding: [0xff,0xff,0x00,0xd8,0x01,0xff,0x00,0x00]

test/MC/Disassembler/AMDGPU/vop1_gfx9.txt

-# RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -disassemble -show-encoding < %s | FileCheck %s -check-prefix=GFX9
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -disassemble -show-encoding < %s | FileCheck %s -check-prefix=GFX9
 
 # GFX9: v_swap_b32 v1, v2 ; encoding: [0x02,0xa3,0x02,0x7e]
 0x02 0xa3 0x02 0x7e

test/MC/Disassembler/AMDGPU/vop3_gfx9.txt

-# RUN: llvm-mc -arch=amdgcn -mcpu=gfx901 -disassemble -show-encoding < %s | FileCheck %s -check-prefix=GFX9
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx900 -disassemble -show-encoding < %s | FileCheck %s -check-prefix=GFX9
 
 # GFX9: v_fma_f16 v5, v1, v2, v3    ; encoding: [0x05,0x00,0x06,0xd2,0x01,0x05,0x0e,0x04]
 0x05,0x00,0x06,0xd2,0x01,0x05,0x0e,0x04
 
 # GFX9: v_fma_f16 v5, -v1, v2, v3    ; encoding: [0x05,0x00,0x06,0xd2,0x01,0x05,0x0e,0x24]
 0x05,0x00,0x06,0xd2,0x01,0x05,0x0e,0x24
 
 # GFX9: v_fma_f16 v5, v1, |v2|, v3    ; encoding: [0x05,0x02,0x06,0xd2,0x01,0x05,0x0e,0x04]