summaryrefslogtreecommitdiffstats
path: root/clang
diff options
context:
space:
mode:
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>2019-01-10 03:25:47 +0000
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>2019-01-10 03:25:47 +0000
commit6332f4d0d48b8c26e946f9f71e0860db9bb7b8e8 (patch)
tree0f9c4ac24fce374d665c5ca383c3d2133da91b52 /clang
parentd3757d3f3a581fffccd3d072479db0fa93995677 (diff)
downloadbcm5719-llvm-6332f4d0d48b8c26e946f9f71e0860db9bb7b8e8.tar.gz
bcm5719-llvm-6332f4d0d48b8c26e946f9f71e0860db9bb7b8e8.zip
[AMDGPU] Separate feature dot-insts
Differential Revision: https://reviews.llvm.org/D56525 llvm-svn: 350794
Diffstat (limited to 'clang')
-rw-r--r--clang/include/clang/Basic/BuiltinsAMDGPU.def14
-rw-r--r--clang/lib/Basic/Targets/AMDGPU.cpp1
-rw-r--r--clang/test/CodeGenOpenCL/amdgpu-features.cl2
-rw-r--r--clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl28
4 files changed, 23 insertions, 22 deletions
diff --git a/clang/include/clang/Basic/BuiltinsAMDGPU.def b/clang/include/clang/Basic/BuiltinsAMDGPU.def
index 1ee43cb5ee6..a25e45fe3fb 100644
--- a/clang/include/clang/Basic/BuiltinsAMDGPU.def
+++ b/clang/include/clang/Basic/BuiltinsAMDGPU.def
@@ -135,13 +135,13 @@ TARGET_BUILTIN(__builtin_amdgcn_fmed3h, "hhhh", "nc", "gfx9-insts")
// Deep learning builtins.
//===----------------------------------------------------------------------===//
-TARGET_BUILTIN(__builtin_amdgcn_fdot2, "fV2hV2hfIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_sdot2, "SiV2SsV2SsSiIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_udot2, "UiV2UsV2UsUiIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_sdot4, "SiSiSiSiIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_udot4, "UiUiUiUiIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_sdot8, "SiSiSiSiIb", "nc", "dl-insts")
-TARGET_BUILTIN(__builtin_amdgcn_udot8, "UiUiUiUiIb", "nc", "dl-insts")
+TARGET_BUILTIN(__builtin_amdgcn_fdot2, "fV2hV2hfIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot2, "SiV2SsV2SsSiIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot2, "UiV2UsV2UsUiIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot4, "SiSiSiSiIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot4, "UiUiUiUiIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot8, "SiSiSiSiIb", "nc", "dot-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot8, "UiUiUiUiIb", "nc", "dot-insts")
//===----------------------------------------------------------------------===//
// Special builtins.
diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
index 4f17b17ff40..7313a692f46 100644
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -137,6 +137,7 @@ bool AMDGPUTargetInfo::initFeatureMap(
switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
case GK_GFX906:
Features["dl-insts"] = true;
+ Features["dot-insts"] = true;
LLVM_FALLTHROUGH;
case GK_GFX909:
case GK_GFX904:
diff --git a/clang/test/CodeGenOpenCL/amdgpu-features.cl b/clang/test/CodeGenOpenCL/amdgpu-features.cl
index e24e2286dff..7aac4d3a368 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-features.cl
@@ -11,7 +11,7 @@
// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx601 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX601 %s
// GFX904: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx9-insts,+s-memrealtime,+vi-insts"
-// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx9-insts,+s-memrealtime,+vi-insts"
+// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx9-insts,+s-memrealtime,+vi-insts"
// GFX801: "target-features"="+16-bit-insts,+ci-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+s-memrealtime,+vi-insts"
// GFX700: "target-features"="+ci-insts,+fp64-fp16-denormals,-fp32-denormals"
// GFX600: "target-features"="+fp64-fp16-denormals,-fp32-denormals"
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
index ca3f4006e30..e2c03a471ba 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
@@ -12,24 +12,24 @@ kernel void builtins_amdgcn_dl_insts_err(
half2 v2hA, half2 v2hB, float fC,
short2 v2ssA, short2 v2ssB, int siA, int siB, int siC,
ushort2 v2usA, ushort2 v2usB, uint uiA, uint uiB, uint uiC) {
- fOut[0] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, false); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dl-insts}}
- fOut[1] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, true); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dl-insts}}
+ fOut[0] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, false); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dot-insts}}
+ fOut[1] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, true); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dot-insts}}
- siOut[0] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, false); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dl-insts}}
- siOut[1] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, true); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dl-insts}}
+ siOut[0] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, false); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dot-insts}}
+ siOut[1] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, true); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dot-insts}}
- uiOut[0] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, false); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dl-insts}}
- uiOut[1] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, true); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dl-insts}}
+ uiOut[0] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, false); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dot-insts}}
+ uiOut[1] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, true); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dot-insts}}
- siOut[2] = __builtin_amdgcn_sdot4(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dl-insts}}
- siOut[3] = __builtin_amdgcn_sdot4(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dl-insts}}
+ siOut[2] = __builtin_amdgcn_sdot4(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dot-insts}}
+ siOut[3] = __builtin_amdgcn_sdot4(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dot-insts}}
- uiOut[2] = __builtin_amdgcn_udot4(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dl-insts}}
- uiOut[3] = __builtin_amdgcn_udot4(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dl-insts}}
+ uiOut[2] = __builtin_amdgcn_udot4(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dot-insts}}
+ uiOut[3] = __builtin_amdgcn_udot4(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dot-insts}}
- siOut[4] = __builtin_amdgcn_sdot8(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dl-insts}}
- siOut[5] = __builtin_amdgcn_sdot8(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dl-insts}}
+ siOut[4] = __builtin_amdgcn_sdot8(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dot-insts}}
+ siOut[5] = __builtin_amdgcn_sdot8(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dot-insts}}
- uiOut[4] = __builtin_amdgcn_udot8(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dl-insts}}
- uiOut[5] = __builtin_amdgcn_udot8(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dl-insts}}
+ uiOut[4] = __builtin_amdgcn_udot8(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dot-insts}}
+ uiOut[5] = __builtin_amdgcn_udot8(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dot-insts}}
}
OpenPOWER on IntegriCloud