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
21 lines
661 B
LLVM
21 lines
661 B
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 | %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"
|
|
target triple = "nvptx-nvidia-cuda"
|
|
|
|
; Make sure predicate (i1) operands to kernels get expanded out to .u8
|
|
|
|
; CHECK: .entry foo
|
|
; CHECK: .param .u8 foo_param_0
|
|
; CHECK: .param .u32 foo_param_1
|
|
define void @foo(i1 %p, i32* %out) {
|
|
%val = zext i1 %p to i32
|
|
store i32 %val, i32* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
!nvvm.annotations = !{!0}
|
|
!0 = !{void (i1, i32*)* @foo, !"kernel", i32 1}
|