llvm-6502/test/CodeGen/SystemZ/vec-const-05.ll
Ulrich Weigand 878c6281d3 [SystemZ] Add CodeGen support for v4f32
The architecture doesn't really have any native v4f32 operations except
v4f32->v2f64 and v2f64->v4f32 conversions, with only half of the v4f32
elements being used.  Even so, using vector registers for <4 x float>
and scalarising individual operations is much better than generating
completely scalar code, since there's much less register pressure.
It's also more efficient to do v4f32 comparisons by extending to 2
v2f64s, comparing those, then packing the result.

This particularly helps with llvmpipe.

Based on a patch by Richard Sandiford.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236523 91177308-0d34-0410-b5e6-96231b3b80d8
2015-05-05 19:27:45 +00:00

48 lines
1.3 KiB
LLVM

; Test vector byte masks, v4f32 version.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
; Test an all-zeros vector.
define <4 x float> @f1() {
; CHECK-LABEL: f1:
; CHECK: vgbm %v24, 0
; CHECK: br %r14
ret <4 x float> zeroinitializer
}
; Test an all-ones vector.
define <4 x float> @f2() {
; CHECK-LABEL: f2:
; CHECK: vgbm %v24, 65535
; CHECK: br %r14
ret <4 x float> <float 0xffffffffe0000000, float 0xffffffffe0000000,
float 0xffffffffe0000000, float 0xffffffffe0000000>
}
; Test a mixed vector (mask 0xc731).
define <4 x float> @f3() {
; CHECK-LABEL: f3:
; CHECK: vgbm %v24, 50993
; CHECK: br %r14
ret <4 x float> <float 0xffffe00000000000, float 0x381fffffe0000000,
float 0x379fffe000000000, float 0x371fe00000000000>
}
; Test that undefs are treated as zero (mask 0xc031).
define <4 x float> @f4() {
; CHECK-LABEL: f4:
; CHECK: vgbm %v24, 49201
; CHECK: br %r14
ret <4 x float> <float 0xffffe00000000000, float undef,
float 0x379fffe000000000, float 0x371fe00000000000>
}
; Test that we don't use VGBM if one of the bytes is not 0 or 0xff.
define <4 x float> @f5() {
; CHECK-LABEL: f5:
; CHECK-NOT: vgbm
; CHECK: br %r14
ret <4 x float> <float 0xffffe00000000000, float 0x381fffffc0000000,
float 0x379fffe000000000, float 0x371fe00000000000>
}