mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-16 11:30:51 +00:00
a017ce21ba
Revert "Remove default in fully-covered switch (to fix Clang -Werror -Wcovered-switch-default)" Revert "R600: Add carry and borrow instructions. Use them to implement UADDO/USUBO" Revert "LegalizeDAG: Try to use Overflow operations when expanding ADD/SUB" Using overflow operations fails CodeGen/Generic/2011-07-07-ScheduleDAGCrash.ll on hexagon, nvptx, and r600. Revert while I investigate. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@234768 91177308-0d34-0410-b5e6-96231b3b80d8
127 lines
4.6 KiB
LLVM
127 lines
4.6 KiB
LLVM
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
|
|
|
|
declare i32 @llvm.r600.read.tidig.x() readnone
|
|
|
|
; FUNC-LABEL: {{^}}test_sub_i32:
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_subrev_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
define void @test_sub_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
|
|
%b_ptr = getelementptr i32, i32 addrspace(1)* %in, i32 1
|
|
%a = load i32, i32 addrspace(1)* %in
|
|
%b = load i32, i32 addrspace(1)* %b_ptr
|
|
%result = sub i32 %a, %b
|
|
store i32 %result, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
; FUNC-LABEL: {{^}}test_sub_v2i32:
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
|
|
define void @test_sub_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <2 x i32>, <2 x i32> addrspace(1) * %in
|
|
%b = load <2 x i32>, <2 x i32> addrspace(1) * %b_ptr
|
|
%result = sub <2 x i32> %a, %b
|
|
store <2 x i32> %result, <2 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_sub_v4i32:
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
; EG: SUB_INT {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
|
|
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
; SI: v_sub_i32_e32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
|
|
|
|
define void @test_sub_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
|
|
%b_ptr = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %in, i32 1
|
|
%a = load <4 x i32>, <4 x i32> addrspace(1) * %in
|
|
%b = load <4 x i32>, <4 x i32> addrspace(1) * %b_ptr
|
|
%result = sub <4 x i32> %a, %b
|
|
store <4 x i32> %result, <4 x i32> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}s_sub_i64:
|
|
; SI: s_sub_u32
|
|
; SI: s_subb_u32
|
|
|
|
; EG-DAG: SETGE_UINT
|
|
; EG-DAG: CNDE_INT
|
|
; EG-DAG: SUB_INT
|
|
; EG-DAG: SUB_INT
|
|
; EG-DAG: SUB_INT
|
|
define void @s_sub_i64(i64 addrspace(1)* noalias %out, i64 %a, i64 %b) nounwind {
|
|
%result = sub i64 %a, %b
|
|
store i64 %result, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_sub_i64:
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
|
|
; EG-DAG: SETGE_UINT
|
|
; EG-DAG: CNDE_INT
|
|
; EG-DAG: SUB_INT
|
|
; EG-DAG: SUB_INT
|
|
; EG-DAG: SUB_INT
|
|
define void @v_sub_i64(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %inA, i64 addrspace(1)* noalias %inB) nounwind {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() readnone
|
|
%a_ptr = getelementptr i64, i64 addrspace(1)* %inA, i32 %tid
|
|
%b_ptr = getelementptr i64, i64 addrspace(1)* %inB, i32 %tid
|
|
%a = load i64, i64 addrspace(1)* %a_ptr
|
|
%b = load i64, i64 addrspace(1)* %b_ptr
|
|
%result = sub i64 %a, %b
|
|
store i64 %result, i64 addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_test_sub_v2i64:
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
define void @v_test_sub_v2i64(<2 x i64> addrspace(1)* %out, <2 x i64> addrspace(1)* noalias %inA, <2 x i64> addrspace(1)* noalias %inB) {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() readnone
|
|
%a_ptr = getelementptr <2 x i64>, <2 x i64> addrspace(1)* %inA, i32 %tid
|
|
%b_ptr = getelementptr <2 x i64>, <2 x i64> addrspace(1)* %inB, i32 %tid
|
|
%a = load <2 x i64>, <2 x i64> addrspace(1)* %a_ptr
|
|
%b = load <2 x i64>, <2 x i64> addrspace(1)* %b_ptr
|
|
%result = sub <2 x i64> %a, %b
|
|
store <2 x i64> %result, <2 x i64> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}v_test_sub_v4i64:
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
; SI: v_sub_i32_e32
|
|
; SI: v_subb_u32_e32
|
|
define void @v_test_sub_v4i64(<4 x i64> addrspace(1)* %out, <4 x i64> addrspace(1)* noalias %inA, <4 x i64> addrspace(1)* noalias %inB) {
|
|
%tid = call i32 @llvm.r600.read.tidig.x() readnone
|
|
%a_ptr = getelementptr <4 x i64>, <4 x i64> addrspace(1)* %inA, i32 %tid
|
|
%b_ptr = getelementptr <4 x i64>, <4 x i64> addrspace(1)* %inB, i32 %tid
|
|
%a = load <4 x i64>, <4 x i64> addrspace(1)* %a_ptr
|
|
%b = load <4 x i64>, <4 x i64> addrspace(1)* %b_ptr
|
|
%result = sub <4 x i64> %a, %b
|
|
store <4 x i64> %result, <4 x i64> addrspace(1)* %out
|
|
ret void
|
|
}
|