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
22 lines
679 B
LLVM
22 lines
679 B
LLVM
; RUN: llc < %s -march=nvptx64 -mcpu=sm_75 -mattr=+ptx70 | FileCheck %s
|
|
; RUN: %if ptxas-11.0 %{ llc < %s -march=nvptx64 -mcpu=sm_75 -mattr=+ptx70 | %ptxas-verify -arch=sm_75 %}
|
|
|
|
declare half @llvm.nvvm.ex2.approx.f16(half)
|
|
declare <2 x half> @llvm.nvvm.ex2.approx.f16x2(<2 x half>)
|
|
|
|
; CHECK-LABEL: exp2_half
|
|
define half @exp2_half(half %0) {
|
|
; CHECK-NOT: call
|
|
; CHECK: ex2.approx.f16
|
|
%res = call half @llvm.nvvm.ex2.approx.f16(half %0);
|
|
ret half %res
|
|
}
|
|
|
|
; CHECK-LABEL: exp2_2xhalf
|
|
define <2 x half> @exp2_2xhalf(<2 x half> %0) {
|
|
; CHECK-NOT: call
|
|
; CHECK: ex2.approx.f16x2
|
|
%res = call <2 x half> @llvm.nvvm.ex2.approx.f16x2(<2 x half> %0);
|
|
ret <2 x half> %res
|
|
}
|