4583f6d344
the `ptx_kernel` calling convention is a more idiomatic and standard way of specifying a NVPTX kernel than using the metadata which is not supposed to change the meaning of the program. Further, checking the calling convention is significantly faster than traversing the metadata, improving compile time. This change updates the clang and mlir frontends as well as the NVPTXCtorDtorLowering pass to emit kernels using the calling convention. In addition, this updates all NVPTX unit tests to use the calling convention as well.
21 lines
742 B
LLVM
21 lines
742 B
LLVM
; RUN: llc < %s -mtriple=nvptx -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_20 -verify-machineinstrs | FileCheck %s
|
|
; RUN: %if ptxas && !ptxas-12.0 %{ llc < %s -mtriple=nvptx -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_20 -verify-machineinstrs | %ptxas-verify %}
|
|
|
|
; CHECK: .func ({{.*}}) device_func
|
|
define float @device_func(float %a) noinline {
|
|
%ret = fmul float %a, %a
|
|
ret float %ret
|
|
}
|
|
|
|
; CHECK: .entry kernel_func
|
|
define ptx_kernel void @kernel_func(ptr %a) {
|
|
%val = load float, ptr %a
|
|
; CHECK: call.uni (retval0),
|
|
; CHECK: device_func,
|
|
%mul = call float @device_func(float %val)
|
|
store float %mul, ptr %a
|
|
ret void
|
|
}
|