squiid/llvm
1
0
Fork 0
Code Issues Pull requests Activity

AMDGPU: Fix target builtins for gfx10

Browse source 
This wasn't setting some of the features from older generations.

llvm-svn: 364123
This commit is contained in:
Matt Arsenault 2019-06-22 01:30:00 +00:00
parent 3df71e0537
commit fc84925208
8 changed files with 14 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
clang/lib/Basic/Targets/AMDGPU.cpp
View file

@ -144,8 +144,10 @@ bool AMDGPUTargetInfo::initFeatureMap(
LLVM_FALLTHROUGH;
case GK_GFX1010:
Features["dl-insts"] = true;
Features["ci-insts"] = true;
Features["16-bit-insts"] = true;
Features["dpp"] = true;
Features["gfx8-insts"] = true;
Features["gfx9-insts"] = true;
Features["gfx10-insts"] = true;
Features["s-memrealtime"] = true;

6
clang/test/CodeGenOpenCL/amdgpu-features.cl
View file

@ -15,9 +15,9 @@
// GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1010: "target-features"="+16-bit-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
// GFX1011: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
// GFX1012: "target-features"="+16-bit-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx9-insts,+s-memrealtime"
// GFX1010: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1011: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX1012: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-insts,+dot5-insts,+dot6-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx10-insts,+gfx8-insts,+gfx9-insts,+s-memrealtime"
// GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx8-insts,+s-memrealtime"
// GFX700: "target-features"="+ci-insts,+fp64-fp16-denormals,-fp32-denormals"
// GFX600: "target-features"="+fp64-fp16-denormals,-fp32-denormals"

1
clang/test/CodeGenOpenCL/builtins-amdgcn-ci.cl
View file

@ -2,6 +2,7 @@
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu hawaii -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu fiji -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
typedef unsigned int uint;

1
clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err-clamp.cl
View file

@ -1,6 +1,7 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -verify -S -emit-llvm -o - %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -verify -S -emit-llvm -o - %s
typedef unsigned int uint;
typedef half __attribute__((ext_vector_type(2))) half2;

1
clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
View file

@ -1,6 +1,7 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -verify -S -emit-llvm -o - %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -verify -S -emit-llvm -o - %s
typedef unsigned int uint;
typedef half __attribute__((ext_vector_type(2))) half2;

2
clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
View file

@ -1,6 +1,8 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1011 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck %s
typedef unsigned int uint;
typedef half __attribute__((ext_vector_type(2))) half2;

1
clang/test/CodeGenOpenCL/builtins-amdgcn-gfx9.cl
View file

@ -1,5 +1,6 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
#pragma OPENCL EXTENSION cl_khr_fp16 : enable

3
clang/test/CodeGenOpenCL/builtins-amdgcn-vi.cl
View file

@ -1,5 +1,8 @@
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu tonga -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx900 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1012 -S -emit-llvm -o - %s | FileCheck %s
#pragma OPENCL EXTENSION cl_khr_fp16 : enable