diff options
Diffstat (limited to 'llvm/docs/NVPTXUsage.rst')
| -rw-r--r-- | llvm/docs/NVPTXUsage.rst | 59 |
1 files changed, 19 insertions, 40 deletions
diff --git a/llvm/docs/NVPTXUsage.rst b/llvm/docs/NVPTXUsage.rst index 629bf2ea5afb..4c8c605edfdd 100644 --- a/llvm/docs/NVPTXUsage.rst +++ b/llvm/docs/NVPTXUsage.rst @@ -57,6 +57,19 @@ not. When compiled, the PTX kernel functions are callable by host-side code. + +Parameter Attributes +-------------------- + +``"nvvm.grid_constant"`` + This attribute may be attached to a ``byval`` parameter of a kernel function + to indicate that the parameter should be lowered as a direct reference to + the grid-constant memory of the parameter, as opposed to a copy of the + parameter in local memory. Writing to a grid-constant parameter is + undefined behavior. Unlike a normal ``byval`` parameter, the address of a + grid-constant parameter is not unique to a given function invocation but + instead is shared by all kernels in the grid. + .. _nvptx_fnattrs: Function Attributes @@ -2289,9 +2302,9 @@ The Kernel ; Intrinsic to read X component of thread ID declare i32 @llvm.nvvm.read.ptx.sreg.tid.x() readnone nounwind - define void @kernel(ptr addrspace(1) %A, - ptr addrspace(1) %B, - ptr addrspace(1) %C) { + define ptx_kernel void @kernel(ptr addrspace(1) %A, + ptr addrspace(1) %B, + ptr addrspace(1) %C) { entry: ; What is my ID? %id = tail call i32 @llvm.nvvm.read.ptx.sreg.tid.x() readnone nounwind @@ -2314,9 +2327,6 @@ The Kernel ret void } - !nvvm.annotations = !{!0} - !0 = !{ptr @kernel, !"kernel", i32 1} - We can use the LLVM ``llc`` tool to directly run the NVPTX code generator: @@ -2442,34 +2452,6 @@ and non-generic address spaces. See :ref:`address_spaces` and :ref:`nvptx_intrinsics` for more information. -Kernel Metadata -^^^^^^^^^^^^^^^ - -In PTX, a function can be either a `kernel` function (callable from the host -program), or a `device` function (callable only from GPU code). You can think -of `kernel` functions as entry-points in the GPU program. To mark an LLVM IR -function as a `kernel` function, we make use of special LLVM metadata. The -NVPTX back-end will look for a named metadata node called -``nvvm.annotations``. This named metadata must contain a list of metadata that -describe the IR. For our purposes, we need to declare a metadata node that -assigns the "kernel" attribute to the LLVM IR function that should be emitted -as a PTX `kernel` function. These metadata nodes take the form: - -.. code-block:: text - - !{<function ref>, metadata !"kernel", i32 1} - -For the previous example, we have: - -.. code-block:: llvm - - !nvvm.annotations = !{!0} - !0 = !{ptr @kernel, !"kernel", i32 1} - -Here, we have a single metadata declaration in ``nvvm.annotations``. This -metadata annotates our ``@kernel`` function with the ``kernel`` attribute. - - Running the Kernel ------------------ @@ -2669,9 +2651,9 @@ Libdevice provides an ``__nv_powf`` function that we will use. ; libdevice function declare float @__nv_powf(float, float) - define void @kernel(ptr addrspace(1) %A, - ptr addrspace(1) %B, - ptr addrspace(1) %C) { + define ptx_kernel void @kernel(ptr addrspace(1) %A, + ptr addrspace(1) %B, + ptr addrspace(1) %C) { entry: ; What is my ID? %id = tail call i32 @llvm.nvvm.read.ptx.sreg.tid.x() readnone nounwind @@ -2694,9 +2676,6 @@ Libdevice provides an ``__nv_powf`` function that we will use. ret void } - !nvvm.annotations = !{!0} - !0 = !{ptr @kernel, !"kernel", i32 1} - To compile this kernel, we perform the following steps: |