ef8655adc8
CUDA-12 no longer supports 32-bit compilation. Tests agnostic to 32/64 compilation mode are switched to use nvptx64. Tests that do care about it have 32-bit ptxas compilation disabled with cuda-12+. Differential Revision: https://reviews.llvm.org/D152199
32 lines
706 B
LLVM
32 lines
706 B
LLVM
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 | %ptxas-verify %}
|
|
|
|
; CHECK: .visible .func foo1
|
|
; CHECK: st.v2.f32
|
|
define void @foo1(<2 x float> %val, ptr %ptr) {
|
|
store <2 x float> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo2
|
|
; CHECK: st.v4.f32
|
|
define void @foo2(<4 x float> %val, ptr %ptr) {
|
|
store <4 x float> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo3
|
|
; CHECK: st.v2.u32
|
|
define void @foo3(<2 x i32> %val, ptr %ptr) {
|
|
store <2 x i32> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
; CHECK: .visible .func foo4
|
|
; CHECK: st.v4.u32
|
|
define void @foo4(<4 x i32> %val, ptr %ptr) {
|
|
store <4 x i32> %val, ptr %ptr
|
|
ret void
|
|
}
|
|
|