forked from OSchip/llvm-project
R600/SI: Expand mul of v2i32/v4i32 for SI
Also add lit test for both cases on SI, and v2i32 for evergreen. Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 184838
This commit is contained in:
parent
00aeb119db
commit
265eef5efe
|
@ -71,6 +71,9 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
|
|||
setOperationAction(ISD::AND, MVT::v2i32, Expand);
|
||||
setOperationAction(ISD::AND, MVT::v4i32, Expand);
|
||||
|
||||
setOperationAction(ISD::MUL, MVT::v2i32, Expand);
|
||||
setOperationAction(ISD::MUL, MVT::v4i32, Expand);
|
||||
|
||||
setOperationAction(ISD::SUB, MVT::v2i32, Expand);
|
||||
setOperationAction(ISD::SUB, MVT::v4i32, Expand);
|
||||
|
||||
|
|
|
@ -1,12 +1,38 @@
|
|||
;RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck %s
|
||||
; RUN: llc < %s -march=r600 -mcpu=redwood | FileCheck --check-prefix=EG-CHECK %s
|
||||
; RUN: llc < %s -march=r600 -mcpu=verde | FileCheck --check-prefix=SI-CHECK %s
|
||||
|
||||
; mul24 and mad24 are affected
|
||||
;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;CHECK: MULLO_INT * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
define void @test(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
|
||||
;EG-CHECK: @test2
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
;SI-CHECK: @test2
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
|
||||
define void @test2(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
|
||||
%b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
|
||||
%a = load <2 x i32> addrspace(1) * %in
|
||||
%b = load <2 x i32> addrspace(1) * %b_ptr
|
||||
%result = mul <2 x i32> %a, %b
|
||||
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
|
||||
ret void
|
||||
}
|
||||
|
||||
;EG-CHECK: @test4
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
;EG-CHECK: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
||||
|
||||
;SI-CHECK: @test4
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
;SI-CHECK: V_MUL_LO_I32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
|
||||
|
||||
define void @test4(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
|
||||
%b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
|
||||
%a = load <4 x i32> addrspace(1) * %in
|
||||
%b = load <4 x i32> addrspace(1) * %b_ptr
|
||||
|
|
Loading…
Reference in New Issue