[PATCH] D57972: [AMDGPU] Split dot-insts feature
Stanislav Mekhanoshin via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Fri Feb 8 12:34:26 PST 2019
rampitec created this revision.
rampitec added reviewers: kzhuravl, b-sumner.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely.
https://reviews.llvm.org/D57972
Files:
include/clang/Basic/BuiltinsAMDGPU.def
lib/Basic/Targets/AMDGPU.cpp
test/CodeGenOpenCL/amdgpu-features.cl
test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
Index: test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
===================================================================
--- test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
+++ test/CodeGenOpenCL/builtins-amdgcn-dl-insts-err.cl
@@ -12,24 +12,24 @@
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 dot-insts}}
- fOut[1] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, true); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dot-insts}}
+ fOut[0] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, false); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dot2-insts}}
+ fOut[1] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, true); // expected-error {{'__builtin_amdgcn_fdot2' needs target feature dot2-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}}
+ siOut[0] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, false); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dot2-insts}}
+ siOut[1] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, true); // expected-error {{'__builtin_amdgcn_sdot2' needs target feature dot2-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}}
+ uiOut[0] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, false); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dot2-insts}}
+ uiOut[1] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, true); // expected-error {{'__builtin_amdgcn_udot2' needs target feature dot2-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}}
+ siOut[2] = __builtin_amdgcn_sdot4(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dot1-insts}}
+ siOut[3] = __builtin_amdgcn_sdot4(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot4' needs target feature dot1-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}}
+ uiOut[2] = __builtin_amdgcn_udot4(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dot2-insts}}
+ uiOut[3] = __builtin_amdgcn_udot4(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot4' needs target feature dot2-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}}
+ siOut[4] = __builtin_amdgcn_sdot8(siA, siB, siC, false); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dot1-insts}}
+ siOut[5] = __builtin_amdgcn_sdot8(siA, siB, siC, true); // expected-error {{'__builtin_amdgcn_sdot8' needs target feature dot1-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}}
+ uiOut[4] = __builtin_amdgcn_udot8(uiA, uiB, uiC, false); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dot2-insts}}
+ uiOut[5] = __builtin_amdgcn_udot8(uiA, uiB, uiC, true); // expected-error {{'__builtin_amdgcn_udot8' needs target feature dot2-insts}}
}
Index: test/CodeGenOpenCL/amdgpu-features.cl
===================================================================
--- test/CodeGenOpenCL/amdgpu-features.cl
+++ 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,+dot-insts,+dpp,+fp32-denormals,+fp64-fp16-denormals,+gfx9-insts,+s-memrealtime,+vi-insts"
+// GFX906: "target-features"="+16-bit-insts,+ci-insts,+dl-insts,+dot1-insts,+dot2-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"
Index: lib/Basic/Targets/AMDGPU.cpp
===================================================================
--- lib/Basic/Targets/AMDGPU.cpp
+++ lib/Basic/Targets/AMDGPU.cpp
@@ -136,7 +136,8 @@
switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
case GK_GFX906:
Features["dl-insts"] = true;
- Features["dot-insts"] = true;
+ Features["dot1-insts"] = true;
+ Features["dot2-insts"] = true;
LLVM_FALLTHROUGH;
case GK_GFX909:
case GK_GFX904:
Index: include/clang/Basic/BuiltinsAMDGPU.def
===================================================================
--- include/clang/Basic/BuiltinsAMDGPU.def
+++ include/clang/Basic/BuiltinsAMDGPU.def
@@ -145,13 +145,13 @@
// Deep learning builtins.
//===----------------------------------------------------------------------===//
-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")
+TARGET_BUILTIN(__builtin_amdgcn_fdot2, "fV2hV2hfIb", "nc", "dot2-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot2, "SiV2SsV2SsSiIb", "nc", "dot2-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot2, "UiV2UsV2UsUiIb", "nc", "dot2-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot4, "SiSiSiSiIb", "nc", "dot1-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot4, "UiUiUiUiIb", "nc", "dot2-insts")
+TARGET_BUILTIN(__builtin_amdgcn_sdot8, "SiSiSiSiIb", "nc", "dot1-insts")
+TARGET_BUILTIN(__builtin_amdgcn_udot8, "UiUiUiUiIb", "nc", "dot2-insts")
//===----------------------------------------------------------------------===//
// Special builtins.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D57972.186030.patch
Type: text/x-patch
Size: 7451 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190208/5bd7acfc/attachment-0001.bin>
More information about the llvm-commits
mailing list