llvm-6502/test/CodeGen/PowerPC/vec_mul.ll
Adhemerval Zanella 375cbe4143 This patch fixes the Altivec addend construction for the fused multiply-add
instruction (vmaddfp) to conform with IEEE to ensure the sign of a zero
result when resulting product is -0.0.

The -0.0 vector addend to vmaddfp is generated by a creating a vector
with full bits sets and then shifting each elements by 31-bits to the
left, resulting in a vector of 0x80000000 (or -0.0 as float).

The 'buildvec_canonicalize.ll' was adjusted to reflect this change and
the 'vec_mul.ll' was complemented with the float vector multiplication
test.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@168998 91177308-0d34-0410-b5e6-96231b3b80d8
2012-11-30 13:05:44 +00:00

47 lines
1.5 KiB
LLVM

; RUN: llc < %s -mattr=+altivec | FileCheck %s
define <4 x i32> @test_v4i32(<4 x i32>* %X, <4 x i32>* %Y) {
%tmp = load <4 x i32>* %X ; <<4 x i32>> [#uses=1]
%tmp2 = load <4 x i32>* %Y ; <<4 x i32>> [#uses=1]
%tmp3 = mul <4 x i32> %tmp, %tmp2 ; <<4 x i32>> [#uses=1]
ret <4 x i32> %tmp3
}
; CHECK: test_v4i32:
; CHECK: vmsumuhm
; CHECK-NOT: mullw
define <8 x i16> @test_v8i16(<8 x i16>* %X, <8 x i16>* %Y) {
%tmp = load <8 x i16>* %X ; <<8 x i16>> [#uses=1]
%tmp2 = load <8 x i16>* %Y ; <<8 x i16>> [#uses=1]
%tmp3 = mul <8 x i16> %tmp, %tmp2 ; <<8 x i16>> [#uses=1]
ret <8 x i16> %tmp3
}
; CHECK: test_v8i16:
; CHECK: vmladduhm
; CHECK-NOT: mullw
define <16 x i8> @test_v16i8(<16 x i8>* %X, <16 x i8>* %Y) {
%tmp = load <16 x i8>* %X ; <<16 x i8>> [#uses=1]
%tmp2 = load <16 x i8>* %Y ; <<16 x i8>> [#uses=1]
%tmp3 = mul <16 x i8> %tmp, %tmp2 ; <<16 x i8>> [#uses=1]
ret <16 x i8> %tmp3
}
; CHECK: test_v16i8:
; CHECK: vmuloub
; CHECK: vmuleub
; CHECK-NOT: mullw
define <4 x float> @test_float(<4 x float>* %X, <4 x float>* %Y) {
%tmp = load <4 x float>* %X
%tmp2 = load <4 x float>* %Y
%tmp3 = fmul <4 x float> %tmp, %tmp2
ret <4 x float> %tmp3
}
; Check the creation of a negative zero float vector by creating a vector of
; all bits set and shifting it 31 bits to left, resulting a an vector of
; 4 x 0x80000000 (-0.0 as float).
; CHECK: test_float:
; CHECK: vspltisw [[ZNEG:[0-9]+]], -1
; CHECK: vslw {{[0-9]+}}, [[ZNEG]], [[ZNEG]]
; CHECK: vmaddfp