0f1b5f115a
ptxas is a proprietary compiler from Nvidia that can compile PTX to machine code (SASS). It has a lot of diagnostics to catch errors in PTX, which can be used to verify PTX output from llc. Set -DPXTAS_EXECUTABLE=/path/to/ptxas CMake option to enable it. If this option is not set, then ptxas is substituted to true which effectively disables all ptxas RUN lines. LLVM_PTXAS_EXECUTABLE environment variable takes precedence over the CMake option, and allows to override ptxas executable that is used for LIT without complete re-configuration. Differential Revision: https://reviews.llvm.org/D121727
33 lines
755 B
LLVM
33 lines
755 B
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
|
|
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
|
|
;; Kernel function using ptx_kernel calling conv
|
|
|
|
; CHECK: .entry kernel_func
|
|
define ptx_kernel void @kernel_func(float* %a) {
|
|
; CHECK: ret
|
|
ret void
|
|
}
|
|
|
|
;; Device function
|
|
; CHECK: .func device_func
|
|
define void @device_func(float* %a) {
|
|
; CHECK: ret
|
|
ret void
|
|
}
|
|
|
|
;; Kernel function using NVVM metadata
|
|
; CHECK: .entry metadata_kernel
|
|
define void @metadata_kernel(float* %a) {
|
|
; CHECK: ret
|
|
ret void
|
|
}
|
|
|
|
|
|
!nvvm.annotations = !{!1}
|
|
|
|
!1 = !{void (float*)* @metadata_kernel, !"kernel", i32 1}
|