mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-31 10:29:25 +00:00
a59d469e9b
for CellSPU modifications: - SPUInstrInfo.td refactoring: "multiclass" really is _your_ friend. - Other improvements based on refactoring effort in SPUISelLowering.cpp, esp. in SPUISelLowering::PerformDAGCombine(), where zero amount shifts and rotates are now eliminiated, other scalar-to-vector-to-scalar silliness is also eliminated. - 64-bit operations are being implemented, _muldi3.c gcc runtime now compiles and generates the right code. More work still needs to be done. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@47532 91177308-0d34-0410-b5e6-96231b3b80d8
90 lines
2.1 KiB
LLVM
90 lines
2.1 KiB
LLVM
; RUN: llvm-as -o - %s | llc -march=cellspu > %t1.s
|
|
; RUN: grep mpy %t1.s | count 44
|
|
; RUN: grep mpyu %t1.s | count 4
|
|
; RUN: grep mpyh %t1.s | count 10
|
|
; RUN: grep mpyhh %t1.s | count 2
|
|
; RUN: grep rotma %t1.s | count 12
|
|
; RUN: grep rotmahi %t1.s | count 4
|
|
; RUN: grep and %t1.s | count 2
|
|
; RUN: grep selb %t1.s | count 6
|
|
; RUN: grep fsmbi %t1.s | count 4
|
|
; RUN: grep shli %t1.s | count 2
|
|
; RUN: grep shlhi %t1.s | count 4
|
|
; RUN: grep ila %t1.s | count 2
|
|
; RUN: grep xsbh %t1.s | count 4
|
|
target datalayout = "E-p:32:32:128-f64:64:128-f32:32:128-i64:32:128-i32:32:128-i16:16:128-i8:8:128-i1:8:128-a0:0:128-v128:128:128-s0:128:128"
|
|
target triple = "spu"
|
|
|
|
; 32-bit multiply instruction generation:
|
|
define <4 x i32> @mpy_v4i32_1(<4 x i32> %arg1, <4 x i32> %arg2) {
|
|
entry:
|
|
%A = mul <4 x i32> %arg1, %arg2
|
|
ret <4 x i32> %A
|
|
}
|
|
|
|
define <4 x i32> @mpy_v4i32_2(<4 x i32> %arg1, <4 x i32> %arg2) {
|
|
entry:
|
|
%A = mul <4 x i32> %arg2, %arg1
|
|
ret <4 x i32> %A
|
|
}
|
|
|
|
define <8 x i16> @mpy_v8i16_1(<8 x i16> %arg1, <8 x i16> %arg2) {
|
|
entry:
|
|
%A = mul <8 x i16> %arg1, %arg2
|
|
ret <8 x i16> %A
|
|
}
|
|
|
|
define <8 x i16> @mpy_v8i16_2(<8 x i16> %arg1, <8 x i16> %arg2) {
|
|
entry:
|
|
%A = mul <8 x i16> %arg2, %arg1
|
|
ret <8 x i16> %A
|
|
}
|
|
|
|
define <16 x i8> @mul_v16i8_1(<16 x i8> %arg1, <16 x i8> %arg2) {
|
|
entry:
|
|
%A = mul <16 x i8> %arg2, %arg1
|
|
ret <16 x i8> %A
|
|
}
|
|
|
|
define <16 x i8> @mul_v16i8_2(<16 x i8> %arg1, <16 x i8> %arg2) {
|
|
entry:
|
|
%A = mul <16 x i8> %arg1, %arg2
|
|
ret <16 x i8> %A
|
|
}
|
|
|
|
define i32 @mul_i32_1(i32 %arg1, i32 %arg2) {
|
|
entry:
|
|
%A = mul i32 %arg2, %arg1
|
|
ret i32 %A
|
|
}
|
|
|
|
define i32 @mul_i32_2(i32 %arg1, i32 %arg2) {
|
|
entry:
|
|
%A = mul i32 %arg1, %arg2
|
|
ret i32 %A
|
|
}
|
|
|
|
define i16 @mul_i16_1(i16 %arg1, i16 %arg2) {
|
|
entry:
|
|
%A = mul i16 %arg2, %arg1
|
|
ret i16 %A
|
|
}
|
|
|
|
define i16 @mul_i16_2(i16 %arg1, i16 %arg2) {
|
|
entry:
|
|
%A = mul i16 %arg1, %arg2
|
|
ret i16 %A
|
|
}
|
|
|
|
define i8 @mul_i8_1(i8 %arg1, i8 %arg2) {
|
|
entry:
|
|
%A = mul i8 %arg2, %arg1
|
|
ret i8 %A
|
|
}
|
|
|
|
define i8 @mul_i8_2(i8 %arg1, i8 %arg2) {
|
|
entry:
|
|
%A = mul i8 %arg1, %arg2
|
|
ret i8 %A
|
|
}
|