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
25 lines
703 B
LLVM
25 lines
703 B
LLVM
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
|
|
|
|
; CHECK: .visible .func (.param .b32 func_retval0) callee
|
|
define i8 @callee(i8 %a) {
|
|
; CHECK: ld.param.u8
|
|
%ret = add i8 %a, 42
|
|
; CHECK: st.param.b32
|
|
ret i8 %ret
|
|
}
|
|
|
|
; CHECK: .visible .func caller
|
|
define void @caller(ptr %a) {
|
|
; CHECK: ld.u8
|
|
%val = load i8, ptr %a
|
|
%ret = tail call i8 @callee(i8 %val)
|
|
; CHECK: ld.param.b32
|
|
store i8 %ret, ptr %a
|
|
ret void
|
|
}
|
|
|
|
|