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
32 lines
766 B
LLVM
32 lines
766 B
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
; CHECK: .visible .func foo1
|
|
; CHECK: st.v2.f32
|
|
define void @foo1(<2 x float> %val, <2 x float>* %ptr) {
|
|
store <2 x float> %val, <2 x float>* %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo2
|
|
; CHECK: st.v4.f32
|
|
define void @foo2(<4 x float> %val, <4 x float>* %ptr) {
|
|
store <4 x float> %val, <4 x float>* %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo3
|
|
; CHECK: st.v2.u32
|
|
define void @foo3(<2 x i32> %val, <2 x i32>* %ptr) {
|
|
store <2 x i32> %val, <2 x i32>* %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo4
|
|
; CHECK: st.v4.u32
|
|
define void @foo4(<4 x i32> %val, <4 x i32>* %ptr) {
|
|
store <4 x i32> %val, <4 x i32>* %ptr
|
|
ret void
|
|
}
|
|
|