mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-26 05:32:25 +00:00
c0021e43ea
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
107 lines
3.4 KiB
LLVM
107 lines
3.4 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=bonaire -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=CI -check-prefix=FUNC %s
|
|
|
|
declare double @llvm.floor.f64(double) nounwind readnone
|
|
declare <2 x double> @llvm.floor.v2f64(<2 x double>) nounwind readnone
|
|
declare <3 x double> @llvm.floor.v3f64(<3 x double>) nounwind readnone
|
|
declare <4 x double> @llvm.floor.v4f64(<4 x double>) nounwind readnone
|
|
declare <8 x double> @llvm.floor.v8f64(<8 x double>) nounwind readnone
|
|
declare <16 x double> @llvm.floor.v16f64(<16 x double>) nounwind readnone
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_f64:
|
|
; CI: v_floor_f64_e32
|
|
|
|
; SI: s_bfe_u32 [[SEXP:s[0-9]+]], {{s[0-9]+}}, 0xb0014
|
|
; SI: s_and_b32 s{{[0-9]+}}, s{{[0-9]+}}, 0x80000000
|
|
; SI: s_add_i32 s{{[0-9]+}}, [[SEXP]], 0xfffffc01
|
|
; SI: s_lshr_b64
|
|
; SI: s_not_b64
|
|
; SI: s_and_b64
|
|
; SI: cmp_lt_i32
|
|
; SI: cndmask_b32
|
|
; SI: cndmask_b32
|
|
; SI: cmp_gt_i32
|
|
; SI: cndmask_b32
|
|
; SI: cndmask_b32
|
|
; SI: v_cmp_lt_f64
|
|
; SI: v_cmp_lg_f64
|
|
; SI: s_and_b64
|
|
; SI: v_cndmask_b32
|
|
; SI: v_cndmask_b32
|
|
; SI: v_add_f64
|
|
; SI: s_endpgm
|
|
define void @ffloor_f64(double addrspace(1)* %out, double %x) {
|
|
%y = call double @llvm.floor.f64(double %x) nounwind readnone
|
|
store double %y, double addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v2f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %x) {
|
|
%y = call <2 x double> @llvm.floor.v2f64(<2 x double> %x) nounwind readnone
|
|
store <2 x double> %y, <2 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FIXME-FUNC-LABEL: {{^}}ffloor_v3f64:
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; FIXME-CI: v_floor_f64_e32
|
|
; define void @ffloor_v3f64(<3 x double> addrspace(1)* %out, <3 x double> %x) {
|
|
; %y = call <3 x double> @llvm.floor.v3f64(<3 x double> %x) nounwind readnone
|
|
; store <3 x double> %y, <3 x double> addrspace(1)* %out
|
|
; ret void
|
|
; }
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v4f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %x) {
|
|
%y = call <4 x double> @llvm.floor.v4f64(<4 x double> %x) nounwind readnone
|
|
store <4 x double> %y, <4 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v8f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v8f64(<8 x double> addrspace(1)* %out, <8 x double> %x) {
|
|
%y = call <8 x double> @llvm.floor.v8f64(<8 x double> %x) nounwind readnone
|
|
store <8 x double> %y, <8 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}ffloor_v16f64:
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
; CI: v_floor_f64_e32
|
|
define void @ffloor_v16f64(<16 x double> addrspace(1)* %out, <16 x double> %x) {
|
|
%y = call <16 x double> @llvm.floor.v16f64(<16 x double> %x) nounwind readnone
|
|
store <16 x double> %y, <16 x double> addrspace(1)* %out
|
|
ret void
|
|
}
|