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.
39 lines
1.7 KiB
LLVM
39 lines
1.7 KiB
LLVM
; RUN: llc < %s -mtriple=nvptx64 -mcpu=sm_60 | FileCheck %s
|
|
; RUN: %if ptxas %{ llc < %s -mtriple=nvptx64 -mcpu=sm_60 | %ptxas-verify %}
|
|
|
|
%struct.Large = type { [16 x double] }
|
|
|
|
; CHECK-LABEL: .entry func_align(
|
|
; CHECK: .param .u64 .ptr .align 1 func_align_param_0
|
|
; CHECK: .param .u64 .ptr .align 2 func_align_param_1
|
|
; CHECK: .param .u64 .ptr .global .align 4 func_align_param_2
|
|
; CHECK: .param .u64 .ptr .shared .align 8 func_align_param_3
|
|
; CHECK: .param .u64 .ptr .const .align 16 func_align_param_4
|
|
; CHECK: .param .u64 .ptr .local .align 32 func_align_param_5
|
|
define ptx_kernel void @func_align(ptr nocapture readonly align 1 %input,
|
|
ptr nocapture align 2 %out,
|
|
ptr addrspace(1) align 4 %global,
|
|
ptr addrspace(3) align 8 %shared,
|
|
ptr addrspace(4) align 16 %const,
|
|
ptr addrspace(5) align 32 %local) {
|
|
entry:
|
|
ret void
|
|
}
|
|
|
|
; CHECK-LABEL: .entry func_noalign(
|
|
; CHECK: .param .u64 .ptr .align 1 func_noalign_param_0
|
|
; CHECK: .param .u64 .ptr .align 1 func_noalign_param_1
|
|
; CHECK: .param .u64 .ptr .global .align 1 func_noalign_param_2
|
|
; CHECK: .param .u64 .ptr .shared .align 1 func_noalign_param_3
|
|
; CHECK: .param .u64 .ptr .const .align 1 func_noalign_param_4
|
|
; CHECK: .param .u64 .ptr .local .align 1 func_noalign_param_5
|
|
define ptx_kernel void @func_noalign(ptr nocapture readonly %input,
|
|
ptr nocapture %out,
|
|
ptr addrspace(1) %global,
|
|
ptr addrspace(3) %shared,
|
|
ptr addrspace(4) %const,
|
|
ptr addrspace(5) %local) {
|
|
entry:
|
|
ret void
|
|
}
|