Identifies kernels which performs device side kernel enqueues and emit
metadata for the associated hidden kernel arguments. Such kernels are
marked with calls-enqueue-kernel function attribute by
AMDGPUOpenCLEnqueueKernelLowering pass and later on
hidden kernel arguments metadata HiddenDefaultQueue and
HiddenCompletionAction are emitted for them.
Differential Revision: https://reviews.llvm.org/D39255
llvm-svn: 316907
static __global int Var = 0;
__global int* Ptr[] = {&Var};
...
In this case Var is a non premptable symbol and so its address can be used as the value of Ptr, with a base relative relocation that will add the delta between the ELF address and the actual load address. Such relocations do not require a symbol.
Differential Revision: https://reviews.llvm.org/D38909
llvm-svn: 315935
- Update docs to match llvm coding style
- Add missing FP16_OVFL bit for gfx9
- Fix the size of the kernel descriptor in the docs
Differential Revision: https://reviews.llvm.org/D38902
llvm-svn: 315822
This patch adds a post-linking pass which replaces the function pointer of enqueued
block kernel with a global variable (runtime handle) and adds
runtime-handle attribute to the enqueued block kernel.
In LLVM CodeGen the runtime-handle metadata will be translated to
RuntimeHandle metadata in code object. Runtime allocates a global buffer
for each kernel with RuntimeHandel metadata and saves the kernel address
required for the AQL packet into the buffer. __enqueue_kernel function
in device library knows that the invoke function pointer in the block
literal is actually runtime handle and loads the kernel address from it
and puts it into AQL packet for dispatching.
This cannot be done in FE since FE cannot create a unique global variable
with external linkage across LLVM modules. The global variable with internal
linkage does not work since optimization passes will try to replace loads
of the global variable with its initialization value.
Differential Revision: https://reviews.llvm.org/D38610
llvm-svn: 315352
1. Correct description of the kernel initial state for FLAT_SCRATCH_INIT.
2. Add link to GFX9 architecture documentation.
3. Update product names.
4. Rename note record from NT_AMD_AMDGPU_METADATA to NT_AMD_AMDGPU_HSA_METADATA and move description to the AMDHSA coding convention section.
5. Minor typo corrections.
Differential Revision: https://reviews.llvm.org/D36549
llvm-svn: 310954
The FirePro and Radeon versions of Hawaii have different 64 bit floating point configurations so use distinct target names for them. Rename the target name for Kabini to accommodate.
Differential Revision: https://reviews.llvm.org/D34016
llvm-svn: 304959
Fixes traps in any block besides the entry block,
and fixes depending on a live-in physical register
by using a virtual register copy.
Also happens to stop emitting a nop in the case
debug trap is not supported.
llvm-svn: 301206
Summary:
Add links to ISA manuals and ABI.
Add text about assembler syntax.
Add info about instructions operands.
Add instruction examples for each encoding.
Update directives section, add missing .amdgpu_hsa_kernel.
Reviewers: tstellarAMD, SamWot, vpykhtin
Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, artem.tamazov, llvm-commits
Differential Revision: https://reviews.llvm.org/D24724
llvm-svn: 281962
Summary:
Address space mapping is described in lib/Target/AMDGPU/AMDGPU.h in
Doxygen comments. This patch adds the description to user guide for
AMDGPU back-end.
Patch By: Vedran Miletić
Reviewers: tstellarAMD, arsenm
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D17046
llvm-svn: 265500
Yaxun Liu