RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00
Code Issues Projects Releases Wiki Activity

R600: Use MUL_IEEE for trig/fdiv intrinsic

Browse Source 
Reviewed-by: Tom Stellard <thomas.stellard at amd.com>
llvm-svn: 176485
This commit is contained in:
Vincent Lejeune 2013-03-05 15:04:37 +00:00
parent 484e21aa38
commit d0d37f790e
2 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/R600/R600Instructions.td
View File

@ -1090,12 +1090,12 @@ class COS_Common <bits<11> inst> : R600_1OP <
multiclass DIV_Common <InstR600 recip_ieee> {
def : Pat<
(int_AMDGPU_div R600_Reg32:$src0, R600_Reg32:$src1),
(MUL R600_Reg32:$src0, (recip_ieee R600_Reg32:$src1))
(MUL_IEEE R600_Reg32:$src0, (recip_ieee R600_Reg32:$src1))
>;
def : Pat<
(fdiv R600_Reg32:$src0, R600_Reg32:$src1),
(MUL R600_Reg32:$src0, (recip_ieee R600_Reg32:$src1))
(MUL_IEEE R600_Reg32:$src0, (recip_ieee R600_Reg32:$src1))
>;
}
@ -1169,12 +1169,12 @@ let Predicates = [isR600] in {
// cards.
class COS_PAT <InstR600 trig> : Pat<
(fcos R600_Reg32:$src),
(trig (MUL (MOV_IMM_I32 CONST.TWO_PI_INV), R600_Reg32:$src))
(trig (MUL_IEEE (MOV_IMM_I32 CONST.TWO_PI_INV), R600_Reg32:$src))
>;
class SIN_PAT <InstR600 trig> : Pat<
(fsin R600_Reg32:$src),
(trig (MUL (MOV_IMM_I32 CONST.TWO_PI_INV), R600_Reg32:$src))
(trig (MUL_IEEE (MOV_IMM_I32 CONST.TWO_PI_INV), R600_Reg32:$src))
>;
//===----------------------------------------------------------------------===//

8
test/CodeGen/R600/fdiv.v4f32.ll
View File

@ -1,13 +1,13 @@
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
;CHECK: RECIP_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: RECIP_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: RECIP_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: RECIP_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL NON-IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;CHECK: MUL_IEEE T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define void @test(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in) {
%b_ptr = getelementptr <4 x float> addrspace(1)* %in, i32 1