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 ```
47 lines
1.6 KiB
LLVM
47 lines
1.6 KiB
LLVM
; RUN: llc -mtriple=amdgcn -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}rcp_uint:
|
|
; GCN: v_rcp_iflag_f32_e32
|
|
define amdgpu_kernel void @rcp_uint(ptr addrspace(1) %in, ptr addrspace(1) %out) #0 {
|
|
%load = load i32, ptr addrspace(1) %in, align 4
|
|
%cvt = uitofp i32 %load to float
|
|
%div = fdiv float 1.000000e+00, %cvt, !fpmath !0
|
|
store float %div, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}rcp_sint:
|
|
; GCN: v_rcp_iflag_f32_e32
|
|
define amdgpu_kernel void @rcp_sint(ptr addrspace(1) %in, ptr addrspace(1) %out) #0 {
|
|
%load = load i32, ptr addrspace(1) %in, align 4
|
|
%cvt = sitofp i32 %load to float
|
|
%div = fdiv float 1.000000e+00, %cvt, !fpmath !0
|
|
store float %div, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}rcp_uint_denorm:
|
|
; GCN-NOT: v_rcp_iflag_f32
|
|
define amdgpu_kernel void @rcp_uint_denorm(ptr addrspace(1) %in, ptr addrspace(1) %out) #1 {
|
|
%load = load i32, ptr addrspace(1) %in, align 4
|
|
%cvt = uitofp i32 %load to float
|
|
%div = fdiv float 1.000000e+00, %cvt
|
|
store float %div, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}rcp_sint_denorm:
|
|
; GCN-NOT: v_rcp_iflag_f32
|
|
define amdgpu_kernel void @rcp_sint_denorm(ptr addrspace(1) %in, ptr addrspace(1) %out) #1 {
|
|
%load = load i32, ptr addrspace(1) %in, align 4
|
|
%cvt = sitofp i32 %load to float
|
|
%div = fdiv float 1.000000e+00, %cvt
|
|
store float %div, ptr addrspace(1) %out, align 4
|
|
ret void
|
|
}
|
|
|
|
!0 = !{float 2.500000e+00}
|
|
|
|
attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" }
|
|
attributes #1 = { "denormal-fp-math-f32"="ieee,ieee" }
|