[llvm] r184579 - [NVPTX] Add support for selecting CUDA vs OCL mode based on triple
Justin Holewinski
jholewinski at nvidia.com
Fri Jun 21 11:51:50 PDT 2013
Author: jholewinski
Date: Fri Jun 21 13:51:49 2013
New Revision: 184579
URL: http://llvm.org/viewvc/llvm-project?rev=184579&view=rev
Log:
[NVPTX] Add support for selecting CUDA vs OCL mode based on triple
IR for CUDA should use "nvptx[64]-nvidia-cuda", and IR for NV OpenCL should use "nvptx[64]-nvidia-nvcl"
Modified:
llvm/trunk/include/llvm/ADT/Triple.h
llvm/trunk/lib/Support/Triple.cpp
llvm/trunk/lib/Target/NVPTX/NVPTX.h
llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp
llvm/trunk/test/CodeGen/NVPTX/generic-to-nvvm.ll
llvm/trunk/test/CodeGen/NVPTX/i1-global.ll
llvm/trunk/test/CodeGen/NVPTX/i1-param.ll
llvm/trunk/test/CodeGen/NVPTX/load-sext-i1.ll
llvm/trunk/test/CodeGen/NVPTX/refl1.ll
Modified: llvm/trunk/include/llvm/ADT/Triple.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/ADT/Triple.h?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/include/llvm/ADT/Triple.h (original)
+++ llvm/trunk/include/llvm/ADT/Triple.h Fri Jun 21 13:51:49 2013
@@ -81,7 +81,8 @@ public:
BGP,
BGQ,
Freescale,
- IBM
+ IBM,
+ NVIDIA
};
enum OSType {
UnknownOS,
@@ -107,7 +108,9 @@ public:
NaCl, // Native Client
CNK, // BG/P Compute-Node Kernel
Bitrig,
- AIX
+ AIX,
+ CUDA, // NVIDIA CUDA
+ NVCL // NVIDIA OpenCL
};
enum EnvironmentType {
UnknownEnvironment,
Modified: llvm/trunk/lib/Support/Triple.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/Triple.cpp?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/lib/Support/Triple.cpp (original)
+++ llvm/trunk/lib/Support/Triple.cpp Fri Jun 21 13:51:49 2013
@@ -104,6 +104,7 @@ const char *Triple::getVendorTypeName(Ve
case BGQ: return "bgq";
case Freescale: return "fsl";
case IBM: return "ibm";
+ case NVIDIA: return "nvidia";
}
llvm_unreachable("Invalid VendorType!");
@@ -135,6 +136,8 @@ const char *Triple::getOSTypeName(OSType
case CNK: return "cnk";
case Bitrig: return "bitrig";
case AIX: return "aix";
+ case CUDA: return "cuda";
+ case NVCL: return "nvcl";
}
llvm_unreachable("Invalid OSType");
@@ -260,6 +263,7 @@ static Triple::VendorType parseVendor(St
.Case("bgq", Triple::BGQ)
.Case("fsl", Triple::Freescale)
.Case("ibm", Triple::IBM)
+ .Case("nvidia", Triple::NVIDIA)
.Default(Triple::UnknownVendor);
}
@@ -287,6 +291,8 @@ static Triple::OSType parseOS(StringRef
.StartsWith("cnk", Triple::CNK)
.StartsWith("bitrig", Triple::Bitrig)
.StartsWith("aix", Triple::AIX)
+ .StartsWith("cuda", Triple::CUDA)
+ .StartsWith("nvcl", Triple::NVCL)
.Default(Triple::UnknownOS);
}
Modified: llvm/trunk/lib/Target/NVPTX/NVPTX.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTX.h?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/lib/Target/NVPTX/NVPTX.h (original)
+++ llvm/trunk/lib/Target/NVPTX/NVPTX.h Fri Jun 21 13:51:49 2013
@@ -77,8 +77,7 @@ extern Target TheNVPTXTarget64;
namespace NVPTX {
enum DrvInterface {
NVCL,
- CUDA,
- TEST
+ CUDA
};
// A field inside TSFlags needs a shift and a mask. The usage is
Modified: llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp (original)
+++ llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp Fri Jun 21 13:51:49 2013
@@ -19,23 +19,18 @@
using namespace llvm;
-// Select Driver Interface
-#include "llvm/Support/CommandLine.h"
-namespace {
-cl::opt<NVPTX::DrvInterface> DriverInterface(
- cl::desc("Choose driver interface:"),
- cl::values(clEnumValN(NVPTX::NVCL, "drvnvcl", "Nvidia OpenCL driver"),
- clEnumValN(NVPTX::CUDA, "drvcuda", "Nvidia CUDA driver"),
- clEnumValN(NVPTX::TEST, "drvtest", "Plain Test"), clEnumValEnd),
- cl::init(NVPTX::NVCL));
-}
NVPTXSubtarget::NVPTXSubtarget(const std::string &TT, const std::string &CPU,
const std::string &FS, bool is64Bit)
: NVPTXGenSubtargetInfo(TT, CPU, FS), Is64Bit(is64Bit), PTXVersion(0),
SmVersion(20) {
- drvInterface = DriverInterface;
+ Triple T(TT);
+
+ if (T.getOS() == Triple::NVCL)
+ drvInterface = NVPTX::NVCL;
+ else
+ drvInterface = NVPTX::CUDA;
// Provide the default CPU if none
std::string defCPU = "sm_20";
Modified: llvm/trunk/test/CodeGen/NVPTX/generic-to-nvvm.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/generic-to-nvvm.ll?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/generic-to-nvvm.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/generic-to-nvvm.ll Fri Jun 21 13:51:49 2013
@@ -1,6 +1,7 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 -drvcuda | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
+target triple = "nvptx-nvidia-cuda"
; Ensure global variables in address space 0 are promoted to address space 1
Modified: llvm/trunk/test/CodeGen/NVPTX/i1-global.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/i1-global.ll?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/i1-global.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/i1-global.ll Fri Jun 21 13:51:49 2013
@@ -1,7 +1,7 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 -drvcuda | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
-
+target triple = "nvptx-nvidia-cuda"
; CHECK: .visible .global .align 1 .u8 mypred
@mypred = addrspace(1) global i1 true, align 1
Modified: llvm/trunk/test/CodeGen/NVPTX/i1-param.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/i1-param.ll?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/i1-param.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/i1-param.ll Fri Jun 21 13:51:49 2013
@@ -1,6 +1,7 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 -drvcuda | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
+target triple = "nvptx-nvidia-cuda"
; Make sure predicate (i1) operands to kernels get expanded out to .u8
Modified: llvm/trunk/test/CodeGen/NVPTX/load-sext-i1.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/load-sext-i1.ll?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/load-sext-i1.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/load-sext-i1.ll Fri Jun 21 13:51:49 2013
@@ -1,7 +1,7 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 -drvcuda | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
-
+target triple = "nvptx-nvidia-cuda"
define void @main(i1* %a1, i32 %a2, i32* %arg3) {
; CHECK: ld.u8
Modified: llvm/trunk/test/CodeGen/NVPTX/refl1.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/NVPTX/refl1.ll?rev=184579&r1=184578&r2=184579&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/NVPTX/refl1.ll (original)
+++ llvm/trunk/test/CodeGen/NVPTX/refl1.ll Fri Jun 21 13:51:49 2013
@@ -1,4 +1,6 @@
-; RUN: llc < %s -march=nvptx -mcpu=sm_20 -drvcuda | FileCheck %s
+; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
+
+target triple = "nvptx-nvidia-cuda"
; Function Attrs: nounwind
; CHECK: .entry foo
More information about the llvm-commits
mailing list