R600/SI: Expand srl 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>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@184841 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Aaron Watry 2013-06-25 13:55:37 +00:00
parent 60e6dacd1c
commit 61de9f83cb
2 changed files with 37 additions and 7 deletions

View File

@ -79,6 +79,8 @@ SITargetLowering::SITargetLowering(TargetMachine &TM) :
setOperationAction(ISD::SHL, MVT::v2i32, Expand);
setOperationAction(ISD::SHL, MVT::v4i32, Expand);
setOperationAction(ISD::SRL, MVT::v4i32, Expand);
setOperationAction(ISD::SRL, MVT::v2i32, Expand);
setOperationAction(ISD::SUB, MVT::v2i32, Expand);
setOperationAction(ISD::SUB, MVT::v4i32, Expand);

View File

@ -1,12 +1,40 @@
; 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
; CHECK: @lshr_v4i32
; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; CHECK: LSHR * T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: @lshr_v2i32
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
define void @lshr_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) {
;SI-CHECK: @lshr_v2i32
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @lshr_v2i32(<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 = lshr <2 x i32> %a, %b
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
ret void
}
;EG-CHECK: @lshr_v4i32
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;EG-CHECK: LSHR {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
;SI-CHECK: @lshr_v4i32
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
;SI-CHECK: V_LSHR_B32_e32 VGPR{{[0-9]+, VGPR[0-9]+, VGPR[0-9]+}}
define void @lshr_v4i32(<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
%result = lshr <4 x i32> %a, %b
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
ret void