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
22 lines
805 B
LLVM
22 lines
805 B
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
|
|
|
|
target triple = "nvptx-unknown-nvcl"
|
|
|
|
declare i32 @llvm.nvvm.suld.1d.i32.trap(i64, i32)
|
|
|
|
; CHECK: .entry foo
|
|
define void @foo(i64 %img, float* %red, i32 %idx) {
|
|
; CHECK: suld.b.1d.b32.trap {%r[[RED:[0-9]+]]}, [foo_param_0, {%r{{[0-9]+}}}]
|
|
%val = tail call i32 @llvm.nvvm.suld.1d.i32.trap(i64 %img, i32 %idx)
|
|
; CHECK: cvt.rn.f32.s32 %f[[REDF:[0-9]+]], %r[[RED]]
|
|
%ret = sitofp i32 %val to float
|
|
; CHECK: st.f32 [%r{{[0-9]+}}], %f[[REDF]]
|
|
store float %ret, float* %red
|
|
ret void
|
|
}
|
|
|
|
!nvvm.annotations = !{!1, !2}
|
|
!1 = !{void (i64, float*, i32)* @foo, !"kernel", i32 1}
|
|
!2 = !{void (i64, float*, i32)* @foo, !"rdwrimage", i32 0}
|