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
31 lines
848 B
LLVM
31 lines
848 B
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_35 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_35 | %ptxas-verify -arch=sm_35 %}
|
|
|
|
; Check load from constant global variables. These loads should be
|
|
; ld.global.nc (aka ldg).
|
|
|
|
@gv_float = external constant float
|
|
@gv_float2 = external constant <2 x float>
|
|
@gv_float4 = external constant <4 x float>
|
|
|
|
; CHECK-LABEL: test_gv_float()
|
|
define float @test_gv_float() {
|
|
; CHECK: ld.global.nc.f32
|
|
%v = load float, float* @gv_float
|
|
ret float %v
|
|
}
|
|
|
|
; CHECK-LABEL: test_gv_float2()
|
|
define <2 x float> @test_gv_float2() {
|
|
; CHECK: ld.global.nc.v2.f32
|
|
%v = load <2 x float>, <2 x float>* @gv_float2
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
; CHECK-LABEL: test_gv_float4()
|
|
define <4 x float> @test_gv_float4() {
|
|
; CHECK: ld.global.nc.v4.f32
|
|
%v = load <4 x float>, <4 x float>* @gv_float4
|
|
ret <4 x float> %v
|
|
}
|