mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-15 20:29:48 +00:00
7c9c6ed761
Essentially the same as the GEP change in r230786.
A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)
import fileinput
import sys
import re
pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")
for line in sys.stdin:
sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))
Reviewers: rafael, dexonsmith, grosser
Differential Revision: http://reviews.llvm.org/D7649
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
69 lines
2.5 KiB
LLVM
69 lines
2.5 KiB
LLVM
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 %s
|
|
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
|
|
|
|
; These tests check that fdiv is expanded correctly and also test that the
|
|
; scheduler is scheduling the RECIP_IEEE and MUL_IEEE instructions in separate
|
|
; instruction groups.
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_f32(float addrspace(1)* %out, float %a, float %b) {
|
|
entry:
|
|
%0 = fdiv float %a, %b
|
|
store float %0, float addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_v2f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Z
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW]}}, KC0[3].Y
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %a, <2 x float> %b) {
|
|
entry:
|
|
%0 = fdiv <2 x float> %a, %b
|
|
store <2 x float> %0, <2 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}fdiv_v4f32:
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: RECIP_IEEE * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
; R600-DAG: MUL_IEEE {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}, PS
|
|
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
; SI-DAG: v_rcp_f32
|
|
; SI-DAG: v_mul_f32
|
|
define void @fdiv_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x float>, <4 x float> addrspace(1)* %in, i32 1
|
|
%a = load <4 x float>, <4 x float> addrspace(1) * %in
|
|
%b = load <4 x float>, <4 x float> addrspace(1) * %b_ptr
|
|
%result = fdiv <4 x float> %a, %b
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|