[AMDGPU] gfx1010 clang target

Differential Revision: https://reviews.llvm.org/D61875

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@360634 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/docs/ClangCommandLineReference.rst b/docs/ClangCommandLineReference.rst
index f153a0cd0724ac353902a25c09315aeb83e266ae..5ec947a7c0bf2551c6c55aaafe9de0504f16ac17 100644 (file)
--- a/docs/ClangCommandLineReference.rst
+++ b/docs/ClangCommandLineReference.rst
@@ -2396,6 +2396,11 @@ Generate code which only uses the general purpose registers (AArch64 only)
 
 AMDGPU
 ------
+.. option:: -mcumode, -mno-cumode
+
+CU wavefront execution mode is used if enabled and WGP wavefront execution mode
+is used if disabled (AMDGPU only)
+
 .. option:: -mxnack, -mno-xnack
 
 Enable XNACK (AMDGPU only)

diff --git a/include/clang/Driver/Options.td b/include/clang/Driver/Options.td
index d76cc4046be4865a0982b120b019887e5dc9f276..8b4007fc40295c51df01b0f2885eb8128ca84e3b 100644 (file)
--- a/include/clang/Driver/Options.td
+++ b/include/clang/Driver/Options.td
@@ -2202,6 +2202,11 @@ def msram_ecc : Flag<["-"], "msram-ecc">, Group<m_amdgpu_Features_Group>,
 def mno_sram_ecc : Flag<["-"], "mno-sram-ecc">, Group<m_amdgpu_Features_Group>,
   HelpText<"Disable SRAM ECC (AMDGPU only)">;
 
+def mcumode : Flag<["-"], "mcumode">, Group<m_amdgpu_Features_Group>,
+  HelpText<"CU wavefront execution mode is used (AMDGPU only)">;
+def mno_cumode : Flag<["-"], "mno-cumode">, Group<m_amdgpu_Features_Group>,
+  HelpText<"WGP wavefront execution mode is used (AMDGPU only)">;
+
 def faltivec : Flag<["-"], "faltivec">, Group<f_Group>, Flags<[DriverOption]>;
 def fno_altivec : Flag<["-"], "fno-altivec">, Group<f_Group>, Flags<[DriverOption]>;
 def maltivec : Flag<["-"], "maltivec">, Group<m_ppc_Features_Group>;

diff --git a/lib/Basic/Targets/AMDGPU.cpp b/lib/Basic/Targets/AMDGPU.cpp
index 922f02f73d4c3a9c87a045e958e010b19735060a..8916b81482e100eadd41e87efd312691d4c27733 100644 (file)
--- a/lib/Basic/Targets/AMDGPU.cpp
+++ b/lib/Basic/Targets/AMDGPU.cpp
@@ -135,6 +135,14 @@ bool AMDGPUTargetInfo::initFeatureMap(
       CPU = "gfx600";
 
     switch (llvm::AMDGPU::parseArchAMDGCN(CPU)) {
+    case GK_GFX1010:
+      Features["dl-insts"] = true;
+      Features["16-bit-insts"] = true;
+      Features["dpp"] = true;
+      Features["gfx9-insts"] = true;
+      Features["gfx10-insts"] = true;
+      Features["s-memrealtime"] = true;
+      break;
     case GK_GFX906:
       Features["dl-insts"] = true;
       Features["dot1-insts"] = true;

diff --git a/lib/Basic/Targets/AMDGPU.h b/lib/Basic/Targets/AMDGPU.h
index e78e7666720deeafd88e80fc1d051e9dedbc5c01..456cb2ebb8b5573d3c00c733e40a486d5a28d4ea 100644 (file)
--- a/lib/Basic/Targets/AMDGPU.h
+++ b/lib/Basic/Targets/AMDGPU.h
@@ -41,7 +41,6 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
   llvm::AMDGPU::GPUKind GPUKind;
   unsigned GPUFeatures;
 
-
   bool hasFP64() const {
     return getTriple().getArch() == llvm::Triple::amdgcn ||
            !!(GPUFeatures & llvm::AMDGPU::FEATURE_FP64);

diff --git a/lib/Driver/ToolChains/HIP.cpp b/lib/Driver/ToolChains/HIP.cpp
index 1e881502ee874f27c9fe31c99864570da709db07..0f8be07ed5d9de0fb689998d01b244f61c84bae9 100644 (file)
--- a/lib/Driver/ToolChains/HIP.cpp
+++ b/lib/Driver/ToolChains/HIP.cpp
@@ -307,8 +307,8 @@ void HIPToolChain::addClangTargetOptions(
   if (BCLibs.empty()) {
     // Get the bc lib file name for ISA version. For example,
     // gfx803 => oclc_isa_version_803.amdgcn.bc.
-    std::string ISAVerBC =
-        "oclc_isa_version_" + GpuArch.drop_front(3).str() + ".amdgcn.bc";
+    std::string GFXVersion = GpuArch.drop_front(3).str();
+    std::string ISAVerBC = "oclc_isa_version_" + GFXVersion + ".amdgcn.bc";
 
     llvm::StringRef FlushDenormalControlBC;
     if (DriverArgs.hasArg(options::OPT_fcuda_flush_denormals_to_zero))

diff --git a/test/CodeGenOpenCL/amdgpu-features.cl b/test/CodeGenOpenCL/amdgpu-features.cl
index bbfcf096abcc5a315976186ff94c07f66fb7d937..0120e09f999aca4ab64e34a5496f1df991f21eb1 100644 (file)
--- a/test/CodeGenOpenCL/amdgpu-features.cl
+++ b/test/CodeGenOpenCL/amdgpu-features.cl
@@ -5,6 +5,7 @@
 
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx904 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx906 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX906 %s
+// RUN: %clang_cc1 -triple amdgcn -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX1010 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx801 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX801 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx700 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX700 %s
 // RUN: %clang_cc1 -triple amdgcn -target-cpu gfx600 -S -emit-llvm -o - %s | FileCheck --check-prefix=GFX600 %s
@@ -12,6 +13,7 @@
 
 // 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"
 // 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"

diff --git a/test/Driver/amdgpu-features.c b/test/Driver/amdgpu-features.c
index 6b0f103fb6bc7cfcbd2d0b4bc7bc05082ced77de..333f03a98670ad3d806ed20640bf8c27167eb18e 100644 (file)
--- a/test/Driver/amdgpu-features.c
+++ b/test/Driver/amdgpu-features.c
@@ -23,3 +23,9 @@
 
 // RUN: %clang -### -target amdgcn -mcpu=gfx700 -mno-sram-ecc %s 2>&1 | FileCheck --check-prefix=NO-SRAM-ECC %s
 // NO-SRAM-ECC: "-target-feature" "-sram-ecc"
+
+// RUN: %clang -### -target amdgcn -mcpu=gfx1010 -mcumode %s 2>&1 | FileCheck --check-prefix=CUMODE %s
+// CUMODE: "-target-feature" "+cumode"
+
+// RUN: %clang -### -target amdgcn -mcpu=gfx1010 -mno-cumode %s 2>&1 | FileCheck --check-prefix=NO-CUMODE %s
+// NO-CUMODE: "-target-feature" "-cumode"

diff --git a/test/Driver/amdgpu-macros.cl b/test/Driver/amdgpu-macros.cl
index 09f28123b15e88f45876639d2aa672c5bf84f4fc..017389f337e909040a73929ff4891f92235bc024 100644 (file)
--- a/test/Driver/amdgpu-macros.cl
+++ b/test/Driver/amdgpu-macros.cl
@@ -176,6 +176,7 @@
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX904 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX906 %s
 // RUN: %clang -E -dM -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX909 %s
+// RUN: %clang -E -dM -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefixes=ARCH-GCN,GFX1010 %s
 
 // GFX600-DAG: #define FP_FAST_FMA 1
 // GFX601-DAG: #define FP_FAST_FMA 1
@@ -193,6 +194,7 @@
 // GFX904-DAG: #define FP_FAST_FMA 1
 // GFX906-DAG: #define FP_FAST_FMA 1
 // GFX909-DAG: #define FP_FAST_FMA 1
+// GFX1010-DAG: #define FP_FAST_FMA 1
 
 // GFX600-DAG: #define FP_FAST_FMAF 1
 // GFX601-NOT: #define FP_FAST_FMAF 1
@@ -210,6 +212,7 @@
 // GFX904-DAG: #define FP_FAST_FMAF 1
 // GFX906-DAG: #define FP_FAST_FMAF 1
 // GFX909-DAG: #define FP_FAST_FMAF 1
+// GFX1010-DAG: #define FP_FAST_FMAF 1
 
 // ARCH-GCN-DAG: #define __AMDGCN__ 1
 // ARCH-GCN-DAG: #define __AMDGPU__ 1
@@ -231,6 +234,7 @@
 // GFX904-DAG: #define __HAS_FMAF__ 1
 // GFX906-DAG: #define __HAS_FMAF__ 1
 // GFX909-DAG: #define __HAS_FMAF__ 1
+// GFX1010-DAG: #define __HAS_FMAF__ 1
 
 // GFX600-DAG: #define __HAS_FP64__ 1
 // GFX601-DAG: #define __HAS_FP64__ 1
@@ -248,6 +252,7 @@
 // GFX904-DAG: #define __HAS_FP64__ 1
 // GFX906-DAG: #define __HAS_FP64__ 1
 // GFX909-DAG: #define __HAS_FP64__ 1
+// GFX1010-DAG: #define __HAS_FP64__ 1
 
 // GFX600-DAG: #define __HAS_LDEXPF__ 1
 // GFX601-DAG: #define __HAS_LDEXPF__ 1
@@ -265,6 +270,7 @@
 // GFX904-DAG: #define __HAS_LDEXPF__ 1
 // GFX906-DAG: #define __HAS_LDEXPF__ 1
 // GFX909-DAG: #define __HAS_LDEXPF__ 1
+// GFX1010-DAG: #define __HAS_LDEXPF__ 1
 
 // GFX600-DAG: #define __gfx600__ 1
 // GFX601-DAG: #define __gfx601__ 1
@@ -282,3 +288,4 @@
 // GFX904-DAG: #define __gfx904__ 1
 // GFX906-DAG: #define __gfx906__ 1
 // GFX909-DAG: #define __gfx909__ 1
+// GFX1010-DAG: #define __gfx1010__ 1

diff --git a/test/Driver/amdgpu-mcpu.cl b/test/Driver/amdgpu-mcpu.cl
index 4191d1884cf495b0e5b440ce3625511b11fc3668..029213ed36ddd26ee80cab2d57fcaa010b24dbfd 100644 (file)
--- a/test/Driver/amdgpu-mcpu.cl
+++ b/test/Driver/amdgpu-mcpu.cl
@@ -85,6 +85,7 @@
 // RUN: %clang -### -target amdgcn -mcpu=gfx904 %s 2>&1 | FileCheck --check-prefix=GFX904 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx906 %s 2>&1 | FileCheck --check-prefix=GFX906 %s
 // RUN: %clang -### -target amdgcn -mcpu=gfx909 %s 2>&1 | FileCheck --check-prefix=GFX909 %s
+// RUN: %clang -### -target amdgcn -mcpu=gfx1010 %s 2>&1 | FileCheck --check-prefix=GFX1010 %s
 
 // GFX600:    "-target-cpu" "gfx600"
 // TAHITI:    "-target-cpu" "tahiti"
@@ -119,3 +120,4 @@
 // GFX904:    "-target-cpu" "gfx904"
 // GFX906:    "-target-cpu" "gfx906"
 // GFX909:    "-target-cpu" "gfx909"
+// GFX1010:   "-target-cpu" "gfx1010"