9e9907f1cf
Similar to 806761a7629df268c8aed49657aeccffa6bca449. For IR files without a target triple, -mtriple= specifies the full target triple while -march= merely sets the architecture part of the default target triple, leaving a target triple which may not make sense, e.g. amdgpu-apple-darwin. Therefore, -march= is error-prone and not recommended for tests without a target triple. The issue has been benign as we recognize $unknown-apple-darwin as ELF instead of rejecting it outrightly. This patch changes AMDGPU tests to not rely on the default OS/environment components. Tests that need fixes are not changed: ``` LLVM :: CodeGen/AMDGPU/fabs.f64.ll LLVM :: CodeGen/AMDGPU/fabs.ll LLVM :: CodeGen/AMDGPU/floor.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.f64.ll LLVM :: CodeGen/AMDGPU/fneg-fabs.ll LLVM :: CodeGen/AMDGPU/r600-infinite-loop-bug-while-reorganizing-vector.ll LLVM :: CodeGen/AMDGPU/schedule-if-2.ll ```
40 lines
1.2 KiB
LLVM
40 lines
1.2 KiB
LLVM
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=BOTH %s
|
|
; RUN: llc -amdgpu-scalarize-global-loads=false -mtriple=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=BOTH %s
|
|
|
|
; BOTH-LABEL: {{^}}s_rotl_i64:
|
|
; BOTH-DAG: s_lshl_b64
|
|
; BOTH-DAG: s_sub_i32
|
|
; BOTH-DAG: s_lshr_b64
|
|
; BOTH: s_or_b64
|
|
; BOTH: s_endpgm
|
|
define amdgpu_kernel void @s_rotl_i64(ptr addrspace(1) %in, i64 %x, i64 %y) {
|
|
entry:
|
|
%0 = shl i64 %x, %y
|
|
%1 = sub i64 64, %y
|
|
%2 = lshr i64 %x, %1
|
|
%3 = or i64 %0, %2
|
|
store i64 %3, ptr addrspace(1) %in
|
|
ret void
|
|
}
|
|
|
|
; BOTH-LABEL: {{^}}v_rotl_i64:
|
|
; SI-DAG: v_lshl_b64
|
|
; VI-DAG: v_lshlrev_b64
|
|
; BOTH-DAG: v_sub_{{[iu]}}32
|
|
; SI: v_lshr_b64
|
|
; VI: v_lshrrev_b64
|
|
; BOTH: v_or_b32
|
|
; BOTH: v_or_b32
|
|
; BOTH: s_endpgm
|
|
define amdgpu_kernel void @v_rotl_i64(ptr addrspace(1) %in, ptr addrspace(1) %xptr, ptr addrspace(1) %yptr) {
|
|
entry:
|
|
%x = load i64, ptr addrspace(1) %xptr, align 8
|
|
%y = load i64, ptr addrspace(1) %yptr, align 8
|
|
%tmp0 = shl i64 %x, %y
|
|
%tmp1 = sub i64 64, %y
|
|
%tmp2 = lshr i64 %x, %tmp1
|
|
%tmp3 = or i64 %tmp0, %tmp2
|
|
store i64 %tmp3, ptr addrspace(1) %in, align 8
|
|
ret void
|
|
}
|