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
17 lines
636 B
LLVM
17 lines
636 B
LLVM
; RUN: llc < %s -march=nvptx64 -mcpu=sm_35 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_35 | %ptxas-verify -arch=sm_35 %}
|
|
|
|
define void @foo(float* nocapture readonly %x_value, double* nocapture %output) #0 {
|
|
%1 = bitcast float* %x_value to <4 x float>*
|
|
%2 = load <4 x float>, <4 x float>* %1, align 16
|
|
%3 = fpext <4 x float> %2 to <4 x double>
|
|
; CHECK-NOT: ld.v2.f32 {%fd{{[0-9]+}}, %fd{{[0-9]+}}}, [%rd{{[0-9]+}}];
|
|
; CHECK: cvt.f64.f32
|
|
; CHECK: cvt.f64.f32
|
|
; CHECK: cvt.f64.f32
|
|
; CHECK: cvt.f64.f32
|
|
%4 = bitcast double* %output to <4 x double>*
|
|
store <4 x double> %3, <4 x double>* %4
|
|
ret void
|
|
}
|