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

AMDGPU/GCN: Bring processors in sync with AMDGPUUsage 

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

Differential Revision: https://reviews.llvm.org/D40046

llvm-svn: 320194
This commit is contained in:
Konstantin Zhuravlyov 2017-12-08 20:52:28 +00:00
parent 5f7fcb2ea9
commit c40d9f2e5d
48 changed files with 80 additions and 112 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
llvm/lib/Target/AMDGPU/AMDGPU.td
View File

@ -540,6 +540,10 @@ 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,
@ -561,10 +565,6 @@ 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,
@ -576,24 +576,12 @@ def FeatureISAVersion9_0_0 : SubtargetFeatureISAVersion <9,0,0,
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.
//===----------------------------------------------------------------------===//

6
llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
View File

@ -66,16 +66,14 @@ public:
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 {

24
llvm/lib/Target/AMDGPU/GCNProcessors.td
View File

@ -53,10 +53,6 @@ def : ProcessorModel<"gfx700", SIQuarterSpeedModel,
[FeatureISAVersion7_0_0]
>;
def : ProcessorModel<"bonaire", SIQuarterSpeedModel,
[FeatureISAVersion7_0_0]
>;
def : ProcessorModel<"kaveri", SIQuarterSpeedModel,
[FeatureISAVersion7_0_0]
>;
@ -85,6 +81,14 @@ 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)).
//===----------------------------------------------------------------------===//
@ -129,10 +133,6 @@ def : ProcessorModel<"polaris11", SIQuarterSpeedModel,
[FeatureISAVersion8_0_3]
>;
def : ProcessorModel<"gfx804", SIQuarterSpeedModel,
[FeatureISAVersion8_0_4]
>;
def : ProcessorModel<"gfx810", SIQuarterSpeedModel,
[FeatureISAVersion8_1_0]
>;
@ -149,14 +149,6 @@ 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]
>;

17
llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
View File

@ -103,12 +103,13 @@ 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))
@ -117,8 +118,10 @@ IsaVersion getIsaVersion(const FeatureBitset &Features) {
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))
@ -127,20 +130,14 @@ IsaVersion getIsaVersion(const FeatureBitset &Features) {
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};

2
llvm/test/CodeGen/AMDGPU/add.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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).

2
llvm/test/CodeGen/AMDGPU/ashr.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/extract_vector_elt-i16.ll
View File

@ -1,6 +1,6 @@
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI -check-prefix=SICIVI %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=SICIVI %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx901 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -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]+]]

2
llvm/test/CodeGen/AMDGPU/fabs.f16.ll
View File

@ -1,6 +1,6 @@
; 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))

4
llvm/test/CodeGen/AMDGPU/fcanonicalize-elimination.ll
View File

@ -1,7 +1,7 @@
; 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]+}}

2
llvm/test/CodeGen/AMDGPU/fcanonicalize.f16.ll
View File

@ -1,5 +1,5 @@
; 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

2
llvm/test/CodeGen/AMDGPU/fcopysign.f16.ll
View File

@ -1,6 +1,6 @@
; 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)

4
llvm/test/CodeGen/AMDGPU/fmed3.ll
View File

@ -2,8 +2,8 @@
; 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:

16
llvm/test/CodeGen/AMDGPU/fmuladd.v2f16.ll
View File

@ -1,12 +1,12 @@
; 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=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=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-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

2
llvm/test/CodeGen/AMDGPU/fneg-fabs.f16.ll
View File

@ -1,6 +1,6 @@
; 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

2
llvm/test/CodeGen/AMDGPU/fneg.f16.ll
View File

@ -1,6 +1,6 @@
; 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:

2
llvm/test/CodeGen/AMDGPU/fpext.f16.ll
View File

@ -1,6 +1,6 @@
; 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]+]]

2
llvm/test/CodeGen/AMDGPU/fptrunc.f16.ll
View File

@ -1,6 +1,6 @@
; 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]+]]

2
llvm/test/CodeGen/AMDGPU/fsub.f16.ll
View File

@ -1,6 +1,6 @@
; 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]+]]

9
llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll
View File

@ -4,6 +4,8 @@
; 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
@ -17,12 +19,9 @@
; 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"
@ -31,13 +30,11 @@
; 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"

2
llvm/test/CodeGen/AMDGPU/immv216.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/inlineasm-packed.ll
View File

@ -1,4 +1,4 @@
; 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]+}}

2
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.pkrtz.ll
View File

@ -1,6 +1,6 @@
; 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}}

2
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.exp.compr.ll
View File

@ -1,6 +1,6 @@
; 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

2
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fmed3.f16.ll
View File

@ -1,4 +1,4 @@
; 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]+}}

2
llvm/test/CodeGen/AMDGPU/lshr.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/max.i16.ll
View File

@ -1,5 +1,5 @@
; 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:

2
llvm/test/CodeGen/AMDGPU/min.ll
View File

@ -1,6 +1,6 @@
; 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:

2
llvm/test/CodeGen/AMDGPU/pack.v2f16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/pack.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/scratch-simple.ll
View File

@ -1,5 +1,5 @@
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=verde -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx804 -mattr=-flat-for-global -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx803 -mattr=-flat-for-global -mattr=+vgpr-spilling -verify-machineinstrs < %s | FileCheck --check-prefix=GCN --check-prefix=SI %s
; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -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

2
llvm/test/CodeGen/AMDGPU/sext-in-reg.ll
View File

@ -1,6 +1,6 @@
; 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.

2
llvm/test/CodeGen/AMDGPU/shl.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/smed3.ll
View File

@ -1,6 +1,6 @@
; 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

2
llvm/test/CodeGen/AMDGPU/sminmax.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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

2
llvm/test/CodeGen/AMDGPU/sub.v2i16.ll
View File

@ -1,4 +1,4 @@
; 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).

2
llvm/test/CodeGen/AMDGPU/umed3.ll
View File

@ -1,6 +1,6 @@
; 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

2
llvm/test/MC/AMDGPU/gfx9_asm_all.s
View File

@ -1,4 +1,4 @@
// 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]

10
llvm/test/MC/AMDGPU/hsa_code_object_isa_args.s
View File

@ -1,8 +1,8 @@
// 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
@ -10,8 +10,8 @@
// 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
@ -22,7 +22,7 @@
// 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

2
llvm/test/MC/AMDGPU/literalv216.s
View File

@ -1,4 +1,4 @@
// 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]

6
llvm/test/MC/AMDGPU/sym_option.s
View File

@ -6,7 +6,6 @@
// 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
@ -18,7 +17,6 @@
// CARRIZO: .byte 8
// TONGA: .byte 8
// FIJI: .byte 8
// GFX804: .byte 8
// STONEY: .byte 8
.byte .option.machine_version_minor
@ -30,17 +28,15 @@
// 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

2
llvm/test/MC/AMDGPU/vop1-gfx9.s
View File

@ -1,4 +1,4 @@
// 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

2
llvm/test/MC/AMDGPU/vop3-gfx9.s
View File

@ -1,4 +1,4 @@
// 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

2
llvm/test/MC/AMDGPU/vop3p-err.s
View File

@ -1,4 +1,4 @@
// 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

2
llvm/test/MC/AMDGPU/vop3p.s
View File

@ -1,4 +1,4 @@
// 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

2
llvm/test/MC/Disassembler/AMDGPU/flat_gfx9.txt
View File

@ -1,4 +1,4 @@
# 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: flat_atomic_add v[0:1], v0 ; encoding: [0x00,0x00,0x08,0xdd,0x00,0x00,0x00,0x00]
0x00,0x00,0x08,0xdd,0x00,0x00,0x00,0x00

2
llvm/test/MC/Disassembler/AMDGPU/gfx9_dasm_all.txt
View File

@ -1,4 +1,4 @@
# 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

2
llvm/test/MC/Disassembler/AMDGPU/vop1_gfx9.txt
View File

@ -1,4 +1,4 @@
# 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

2
llvm/test/MC/Disassembler/AMDGPU/vop3_gfx9.txt
View File

@ -1,4 +1,4 @@
# 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