mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-09-01 19:29:22 +00:00
This is a union of these commits: * R600/SI: Enable more tests for VI which need no changes * R600/SI: Enable V_BCNT tests for VI Differences: - v_bcnt_..._e32 -> _e64 - s_load_dword* inline offset is in bytes instead of dwords * R600/SI: Enable all tests for VI which use S_LOAD_DWORD The inline offset is changed from dwords to bytes. * R600/SI: Enable LDS tests for VI Differences: - the s_load_dword inline offset changed from dwords to bytes - the tests checked very little on CI, so they have been fixed to check all instructions that "SI" checked * R600/SI: Enable lshr tests for VI * R600/SI: Fix divrem64 tests - "v_lshl_64" was missing "b" before "64" - added VI-NOT checks * R600/SI: Enable the SI.tid test for VI * R600/SI: Enable the frem test for VI Also, the frem_f64 checking is added for CI-VI. * R600/SI: Add VI tests for rsq.clamped git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228830 91177308-0d34-0410-b5e6-96231b3b80d8
24 lines
1.0 KiB
LLVM
24 lines
1.0 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.AMDGPU.rsq.clamped.f64(double) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}rsq_clamped_f64:
|
|
; SI: v_rsq_clamp_f64_e32
|
|
|
|
; VI: v_rsq_f64_e32 [[RSQ:v\[[0-9]+:[0-9]+\]]], s[2:3]
|
|
; TODO: this constant should be folded:
|
|
; VI: s_mov_b32 s[[ALLBITS:[0-9+]]], -1
|
|
; VI: s_mov_b32 s[[HIGH1:[0-9+]]], 0x7fefffff
|
|
; VI: s_mov_b32 s[[LOW1:[0-9+]]], s[[ALLBITS]]
|
|
; VI: v_min_f64 v[0:1], [[RSQ]], s{{\[}}[[LOW1]]:[[HIGH1]]]
|
|
; VI: s_mov_b32 s[[HIGH2:[0-9+]]], 0xffefffff
|
|
; VI: s_mov_b32 s[[LOW2:[0-9+]]], s[[ALLBITS]]
|
|
; VI: v_max_f64 v[0:1], v[0:1], s{{\[}}[[LOW2]]:[[HIGH2]]]
|
|
|
|
define void @rsq_clamped_f64(double addrspace(1)* %out, double %src) nounwind {
|
|
%rsq_clamped = call double @llvm.AMDGPU.rsq.clamped.f64(double %src) nounwind readnone
|
|
store double %rsq_clamped, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|