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
15 lines
595 B
LLVM
15 lines
595 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 (.param .align 16 .b8 func_retval0[16]) foo0(
|
|
; CHECK: .param .align 4 .b8 foo0_param_0[8]
|
|
define <4 x float> @foo0({float, float} %arg0) {
|
|
ret <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
|
|
}
|
|
|
|
; CHECK: .visible .func (.param .align 8 .b8 func_retval0[8]) foo1(
|
|
; CHECK: .param .align 8 .b8 foo1_param_0[16]
|
|
define <2 x float> @foo1({float, float, i64} %arg0) {
|
|
ret <2 x float> <float 1.0, float 1.0>
|
|
}
|