| /external/llvm/test/CodeGen/NVPTX/ |
| D | envreg.ll | 4 declare i32 @llvm.nvvm.read.ptx.sreg.envreg0()
5 declare i32 @llvm.nvvm.read.ptx.sreg.envreg1()
6 declare i32 @llvm.nvvm.read.ptx.sreg.envreg2()
7 declare i32 @llvm.nvvm.read.ptx.sreg.envreg3()
8 declare i32 @llvm.nvvm.read.ptx.sreg.envreg4()
9 declare i32 @llvm.nvvm.read.ptx.sreg.envreg5()
10 declare i32 @llvm.nvvm.read.ptx.sreg.envreg6()
11 declare i32 @llvm.nvvm.read.ptx.sreg.envreg7()
12 declare i32 @llvm.nvvm.read.ptx.sreg.envreg8()
13 declare i32 @llvm.nvvm.read.ptx.sreg.envreg9()
[all …]
|
| D | intrinsic-old.ll | 11 ; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.tid.x(), !range ![[BLK_IDX_XY:[0-9]+]]
13 %x = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
19 ; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.tid.y(), !range ![[BLK_IDX_XY]]
21 %x = call i32 @llvm.nvvm.read.ptx.sreg.tid.y()
27 ; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.tid.z(), !range ![[BLK_IDX_Z:[0-9]+]]
29 %x = call i32 @llvm.nvvm.read.ptx.sreg.tid.z()
36 %x = call i32 @llvm.nvvm.read.ptx.sreg.tid.w()
42 ; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.ntid.x(), !range ![[BLK_SIZE_XY:[0-9]+]]
44 %x = call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
50 ; RANGE: call i32 @llvm.nvvm.read.ptx.sreg.ntid.y(), !range ![[BLK_SIZE_XY]]
[all …]
|
| D | bug22322.ll | 13 %0 = tail call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
14 %1 = tail call i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
16 %3 = tail call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
40 declare i32 @llvm.nvvm.read.ptx.sreg.ctaid.x() #1
43 declare i32 @llvm.nvvm.read.ptx.sreg.ntid.x() #1
46 declare i32 @llvm.nvvm.read.ptx.sreg.tid.x() #1
|
| /external/swiftshader/third_party/LLVM/test/CodeGen/PTX/ |
| D | intrinsic.ll | 6 %x = call i32 @llvm.ptx.read.tid.x()
13 %x = call i32 @llvm.ptx.read.tid.y()
20 %x = call i32 @llvm.ptx.read.tid.z()
27 %x = call i32 @llvm.ptx.read.tid.w()
34 %x = call i32 @llvm.ptx.read.ntid.x()
41 %x = call i32 @llvm.ptx.read.ntid.y()
48 %x = call i32 @llvm.ptx.read.ntid.z()
55 %x = call i32 @llvm.ptx.read.ntid.w()
62 %x = call i32 @llvm.ptx.read.laneid()
69 %x = call i32 @llvm.ptx.read.warpid()
[all …]
|
| /external/tensorflow/tensorflow/stream_executor/ |
| D | kernel_spec.cc | 50 CudaPtxInMemory::CudaPtxInMemory(port::StringPiece ptx, in CudaPtxInMemory() argument
58 decompressed_ptx_[ptx.data()] = ""; in CudaPtxInMemory()
60 ptx_by_compute_capability_[kMinimumCapability] = ptx.data(); in CudaPtxInMemory()
70 port::StringPiece ptx; in CudaPtxInMemory() local
71 std::tie(major, minor, ptx) = spec; in CudaPtxInMemory()
75 decompressed_ptx_[ptx.data()] = ""; in CudaPtxInMemory()
77 ptx_by_compute_capability_[std::tuple<int, int>{major, minor}] = ptx.data(); in CudaPtxInMemory()
81 string CudaPtxInMemory::DecompressPtx(const char *ptx) { in DecompressPtx() argument
83 uint64 ptx_length = *reinterpret_cast<const uint64 *>(ptx); in DecompressPtx()
85 string compressed_ptx(ptx + sizeof(uint64), in DecompressPtx()
[all …]
|
| D | kernel_spec.h | 157 CudaPtxInMemory(port::StringPiece ptx, port::StringPiece kernelname,
196 static string DecompressPtx(const char *ptx);
344 MultiKernelLoaderSpec *AddCudaPtxInMemory(port::StringPiece ptx,
347 port::StringPiece ptx, port::StringPiece kernelname);
|
| /external/tensorflow/tensorflow/compiler/xla/service/gpu/ |
| D | gpu_compiler.h | 101 std::vector<uint8> CompilePtxOrGetCachedResult(const string& ptx,
117 CompilationCacheKey(std::string ptx, int cc_major, int cc_minor) in CompilationCacheKey()
118 : ptx(std::move(ptx)), cc_major(cc_major), cc_minor(cc_minor) {} in CompilationCacheKey()
119 string ptx; member
126 tensorflow::Hash64Combine(tensorflow::Hash64(key.ptx), key.cc_major), in operator()
134 a.ptx == b.ptx; in operator()
|
| D | gpu_compiler.cc | 400 StatusOr<std::vector<uint8>> CompilePtx(const string& ptx, int cc_major, in CompilePtx() argument
420 TF_RETURN_IF_ERROR(tensorflow::WriteStringToFile(env, ptx_path, ptx)); in CompilePtx()
609 string ptx; in RunBackend() local
612 TF_ASSIGN_OR_RETURN(ptx, CompileToPtx(&llvm_module, {cc_major, cc_minor}, in RunBackend()
629 XLA_VLOG_LINES(2, ptx); in RunBackend()
638 TF_RETURN_IF_ERROR(tensorflow::WriteStringToFile(env, ptx_outfile, ptx)); in RunBackend()
648 CompilePtxOrGetCachedResult(ptx, cc_major, cc_minor); in RunBackend()
668 ptx, cubin, {cc_major, cc_minor}, std::move(thunk_schedule), in RunBackend()
678 std::vector<uint8> GpuCompiler::CompilePtxOrGetCachedResult(const string& ptx, in CompilePtxOrGetCachedResult() argument
694 std::forward_as_tuple(ptx, cc_major, cc_minor), in CompilePtxOrGetCachedResult()
[all …]
|
| D | kernel_thunk.cc | 46 tensorflow::StringPiece ptx = executable.ptx(); in Initialize() local
50 se::port::StringPiece(ptx.data(), ptx.size()), kernel_name_); in Initialize()
|
| D | gpu_executable.h | 52 GpuExecutable(const string& ptx, const std::vector<uint8>& cubin,
69 tensorflow::StringPiece ptx() const { return ptx_; } in ptx() function
|
| /external/llvm/test/Analysis/DivergenceAnalysis/NVPTX/ |
| D | diverge.ll | 10 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
32 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.y()
53 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.z()
103 %laneid = call i32 @llvm.nvvm.read.ptx.sreg.laneid()
125 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
161 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
192 %tid = call i32 @llvm.nvvm.read.ptx.sreg.tid.x()
208 declare i32 @llvm.nvvm.read.ptx.sreg.tid.x()
209 declare i32 @llvm.nvvm.read.ptx.sreg.tid.y()
210 declare i32 @llvm.nvvm.read.ptx.sreg.tid.z()
[all …]
|
| /external/libldac/src/ |
| D | ldacBT_internal.c | 306 LDACBT_TX_INFO *ptx; local
315 ptx = &hLdacBT->tx;
361 ptx->nfrm_in_pkt = ptx->tx_size / hLdacBT->frmlen_tx;
362 if( ptx->nfrm_in_pkt > LDACBT_NFRM_TX_MAX ){
363 ptx->nfrm_in_pkt = LDACBT_NFRM_TX_MAX;
365 else if( ptx->nfrm_in_pkt < 2 ){
367 if( frmlen <= (ptx->tx_size / 2 - LDACBT_FRMHDRBYTES)){
370 frmlen = ptx->tx_size / 2 - LDACBT_FRMHDRBYTES;
375 hLdacBT->eqmid = ldacBT_get_eqmid_from_frmlen( frmlen, ch, hLdacBT->transport, ptx->pkt_type );
|
| /external/llvm/docs/ |
| D | NVPTXUsage.rst | 196 '``llvm.nvvm.read.ptx.sreg.*``'
204 declare i32 @llvm.nvvm.read.ptx.sreg.tid.x()
205 declare i32 @llvm.nvvm.read.ptx.sreg.tid.y()
206 declare i32 @llvm.nvvm.read.ptx.sreg.tid.z()
207 declare i32 @llvm.nvvm.read.ptx.sreg.ntid.x()
208 declare i32 @llvm.nvvm.read.ptx.sreg.ntid.y()
209 declare i32 @llvm.nvvm.read.ptx.sreg.ntid.z()
210 declare i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
211 declare i32 @llvm.nvvm.read.ptx.sreg.ctaid.y()
212 declare i32 @llvm.nvvm.read.ptx.sreg.ctaid.z()
[all …]
|
| /external/tensorflow/tensorflow/compiler/xla/service/gpu/llvm_gpu_backend/ |
| D | gpu_backend_lib.cc | 262 std::string ptx; // need a std::string instead of a ::string. in EmitModuleToPTX() local
264 llvm::raw_string_ostream stream(ptx); in EmitModuleToPTX()
281 return ptx; in EmitModuleToPTX()
492 string ptx; in CompileToPtx() local
500 ptx, CompileModuleToPtx(module, compute_capability, hlo_module_config, in CompileToPtx()
503 return ptx; in CompileToPtx()
|
| /external/tensorflow/tensorflow/stream_executor/cuda/ |
| D | cuda_gpu_executor.cc | 248 const char *ptx = spec.cuda_ptx_in_memory().text(cc_major_, cc_minor_); in GetKernel() local
249 if (ptx == nullptr) { in GetKernel()
250 ptx = spec.cuda_ptx_in_memory().default_text(); in GetKernel()
252 if (ptx == nullptr) { in GetKernel()
259 std::tie(module, module_refcount) = gpu_binary_to_module_[ptx]; in GetKernel()
262 if (!CUDADriver::LoadPtx(context_, ptx, &module)) { in GetKernel()
266 VLOG(3) << "Loaded PTX " << static_cast<const void *>(ptx) in GetKernel()
271 VLOG(3) << "PTX " << static_cast<const void *>(ptx) in GetKernel()
274 kernel_to_gpu_binary_[kernel] = ptx; in GetKernel()
275 gpu_binary_to_module_[ptx] = {module, module_refcount}; in GetKernel()
|
| /external/swiftshader/third_party/LLVM/include/llvm/ |
| D | IntrinsicsPTX.td | 14 let TargetPrefix = "ptx" in {
90 let TargetPrefix = "ptx" in
|
| /external/mesa3d/src/gallium/drivers/nouveau/nv30/ |
| D | nv30_miptree.c | 83 nv30_transfer(struct pipe_transfer *ptx) in nv30_transfer() argument
85 return (struct nv30_transfer *)ptx; in nv30_transfer()
337 struct pipe_transfer *ptx) in nv30_miptree_transfer_unmap() argument
340 struct nv30_transfer *tx = nv30_transfer(ptx); in nv30_miptree_transfer_unmap()
342 if (ptx->usage & PIPE_TRANSFER_WRITE) { in nv30_miptree_transfer_unmap()
351 pipe_resource_reference(&ptx->resource, NULL); in nv30_miptree_transfer_unmap()
|
| /external/mesa3d/src/gallium/drivers/nouveau/nvc0/ |
| D | nvc0_resource.h | 56 struct pipe_transfer *ptx);
|
| /external/protobuf/gtest/build-aux/ |
| D | config.sub | 230 -ptx*)
1656 os=-ptx
1754 -ptx*)
|
| /external/vulkan-validation-layers/tests/gtest-1.7.0/build-aux/ |
| D | config.sub | 231 -ptx*)
1638 os=-ptx
1736 -ptx*)
|
| /external/libmicrohttpd/ |
| D | config.sub | 230 -ptx*)
1664 os=-ptx
1762 -ptx*)
|
| /external/google-breakpad/autotools/ |
| D | config.sub | 230 -ptx*)
1681 os=-ptx
1779 -ptx*)
|
| /external/libcap-ng/libcap-ng-0.7/ |
| D | config.sub | 229 -ptx*)
1631 os=-ptx
1729 -ptx*)
|
| /external/python/cpython2/Modules/_ctypes/libffi/ |
| D | config.sub | 230 -ptx*)
1653 os=-ptx
1751 -ptx*)
|
| /external/libedit/ |
| D | config.sub | 230 -ptx*)
1653 os=-ptx
1751 -ptx*)
|