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
29 lines
1.1 KiB
LLVM
29 lines
1.1 KiB
LLVM
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -nvptx-fma-level=1 | FileCheck %s -check-prefix=FMA
|
|
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -nvptx-fma-level=0 | FileCheck %s -check-prefix=MUL
|
|
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -nvptx-fma-level=1 | FileCheck %s -check-prefix=FMA
|
|
; RUN: llc < %s -march=nvptx64 -mcpu=sm_20 -nvptx-fma-level=0 | FileCheck %s -check-prefix=MUL
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 -nvptx-fma-level=1 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx -mcpu=sm_20 -nvptx-fma-level=0 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 -nvptx-fma-level=1 | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -march=nvptx64 -mcpu=sm_20 -nvptx-fma-level=0 | %ptxas-verify %}
|
|
|
|
define ptx_device float @test_mul_add_f(float %x, float %y, float %z) {
|
|
entry:
|
|
; FMA: fma.rn.f32
|
|
; MUL: mul.rn.f32
|
|
; MUL: add.rn.f32
|
|
%a = fmul float %x, %y
|
|
%b = fadd float %a, %z
|
|
ret float %b
|
|
}
|
|
|
|
define ptx_device double @test_mul_add_d(double %x, double %y, double %z) {
|
|
entry:
|
|
; FMA: fma.rn.f64
|
|
; MUL: mul.rn.f64
|
|
; MUL: add.rn.f64
|
|
%a = fmul double %x, %y
|
|
%b = fadd double %a, %z
|
|
ret double %b
|
|
}
|