llvm/test/Assembler/AutoUpgradeIntrinsics.ll
Dale Johannesen 0488fb649a Massive rewrite of MMX:
The x86_mmx type is used for MMX intrinsics, parameters and
return values where these use MMX registers, and is also
supported in load, store, and bitcast.

Only the above operations generate MMX instructions, and optimizations
do not operate on or produce MMX intrinsics. 

MMX-sized vectors <2 x i32> etc. are lowered to XMM or split into
smaller pieces.  Optimizations may occur on these forms and the
result casted back to x86_mmx, provided the result feeds into a
previous existing x86_mmx operation.

The point of all this is prevent optimizations from introducing
MMX operations, which is unsafe due to the EMMS problem.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@115243 91177308-0d34-0410-b5e6-96231b3b80d8
2010-09-30 23:57:10 +00:00

82 lines
3.4 KiB
LLVM

; Tests to make sure intrinsics are automatically upgraded.
; RUN: llvm-as < %s | llvm-dis | not grep {i32 @llvm\\.ct}
; RUN: llvm-as < %s | llvm-dis | \
; RUN: not grep {llvm\\.part\\.set\\.i\[0-9\]*\\.i\[0-9\]*\\.i\[0-9\]*}
; RUN: llvm-as < %s | llvm-dis | \
; RUN: not grep {llvm\\.part\\.select\\.i\[0-9\]*\\.i\[0-9\]*}
; RUN: llvm-as < %s | llvm-dis | \
; RUN: not grep {llvm\\.bswap\\.i\[0-9\]*\\.i\[0-9\]*}
; RUN: llvm-as < %s | llvm-dis | \
; RUN: grep {llvm\\.x86\\.mmx\\.ps} | grep {x86_mmx} | count 16
declare i32 @llvm.ctpop.i28(i28 %val)
declare i32 @llvm.cttz.i29(i29 %val)
declare i32 @llvm.ctlz.i30(i30 %val)
define i32 @test_ct(i32 %A) {
%c1 = call i32 @llvm.ctpop.i28(i28 1234)
%c2 = call i32 @llvm.cttz.i29(i29 2345)
%c3 = call i32 @llvm.ctlz.i30(i30 3456)
%r1 = add i32 %c1, %c2
%r2 = add i32 %r1, %c3
ret i32 %r2
}
declare i32 @llvm.part.set.i32.i32.i32(i32 %x, i32 %rep, i32 %hi, i32 %lo)
declare i16 @llvm.part.set.i16.i16.i16(i16 %x, i16 %rep, i32 %hi, i32 %lo)
define i32 @test_part_set(i32 %A, i16 %B) {
%a = call i32 @llvm.part.set.i32.i32.i32(i32 %A, i32 27, i32 8, i32 0)
%b = call i16 @llvm.part.set.i16.i16.i16(i16 %B, i16 27, i32 8, i32 0)
%c = zext i16 %b to i32
%d = add i32 %a, %c
ret i32 %d
}
declare i32 @llvm.part.select.i32.i32(i32 %x, i32 %hi, i32 %lo)
declare i16 @llvm.part.select.i16.i16(i16 %x, i32 %hi, i32 %lo)
define i32 @test_part_select(i32 %A, i16 %B) {
%a = call i32 @llvm.part.select.i32.i32(i32 %A, i32 8, i32 0)
%b = call i16 @llvm.part.select.i16.i16(i16 %B, i32 8, i32 0)
%c = zext i16 %b to i32
%d = add i32 %a, %c
ret i32 %d
}
declare i32 @llvm.bswap.i32.i32(i32 %x)
declare i16 @llvm.bswap.i16.i16(i16 %x)
define i32 @test_bswap(i32 %A, i16 %B) {
%a = call i32 @llvm.bswap.i32.i32(i32 %A)
%b = call i16 @llvm.bswap.i16.i16(i16 %B)
%c = zext i16 %b to i32
%d = add i32 %a, %c
ret i32 %d
}
declare <4 x i16> @llvm.x86.mmx.psra.w(<4 x i16>, <2 x i32>) nounwind readnone
declare <4 x i16> @llvm.x86.mmx.psll.w(<4 x i16>, <2 x i32>) nounwind readnone
declare <4 x i16> @llvm.x86.mmx.psrl.w(<4 x i16>, <2 x i32>) nounwind readnone
define void @sh16(<4 x i16> %A, <2 x i32> %B) {
%r1 = call <4 x i16> @llvm.x86.mmx.psra.w( <4 x i16> %A, <2 x i32> %B ) ; <<4 x i16>> [#uses=0]
%r2 = call <4 x i16> @llvm.x86.mmx.psll.w( <4 x i16> %A, <2 x i32> %B ) ; <<4 x i16>> [#uses=0]
%r3 = call <4 x i16> @llvm.x86.mmx.psrl.w( <4 x i16> %A, <2 x i32> %B ) ; <<4 x i16>> [#uses=0]
ret void
}
declare <2 x i32> @llvm.x86.mmx.psra.d(<2 x i32>, <2 x i32>) nounwind readnone
declare <2 x i32> @llvm.x86.mmx.psll.d(<2 x i32>, <2 x i32>) nounwind readnone
declare <2 x i32> @llvm.x86.mmx.psrl.d(<2 x i32>, <2 x i32>) nounwind readnone
define void @sh32(<2 x i32> %A, <2 x i32> %B) {
%r1 = call <2 x i32> @llvm.x86.mmx.psra.d( <2 x i32> %A, <2 x i32> %B ) ; <<2 x i32>> [#uses=0]
%r2 = call <2 x i32> @llvm.x86.mmx.psll.d( <2 x i32> %A, <2 x i32> %B ) ; <<2 x i32>> [#uses=0]
%r3 = call <2 x i32> @llvm.x86.mmx.psrl.d( <2 x i32> %A, <2 x i32> %B ) ; <<2 x i32>> [#uses=0]
ret void
}
declare <1 x i64> @llvm.x86.mmx.psll.q(<1 x i64>, <2 x i32>) nounwind readnone
declare <1 x i64> @llvm.x86.mmx.psrl.q(<1 x i64>, <2 x i32>) nounwind readnone
define void @sh64(<1 x i64> %A, <2 x i32> %B) {
%r1 = call <1 x i64> @llvm.x86.mmx.psll.q( <1 x i64> %A, <2 x i32> %B ) ; <<1 x i64>> [#uses=0]
%r2 = call <1 x i64> @llvm.x86.mmx.psrl.q( <1 x i64> %A, <2 x i32> %B ) ; <<1 x i64>> [#uses=0]
ret void
}