llvm-6502/test/CodeGen/X86/avx-blend.ll
Andrea Di Biagio 825b93b2df [X86] Teach how to combine a vselect into a movss/movsd
Add target specific rules for combining vselect dag nodes into movss/movsd
when possible.

If the vector type of the vselect dag node in input is either MVT::v4i13 or
MVT::v4f32, then try to fold according to rules:

  1) fold (vselect (build_vector (0, -1, -1, -1)), A, B) -> (movss A, B)
  2) fold (vselect (build_vector (-1, 0, 0, 0)), A, B) -> (movss B, A)

If the vector type of the vselect dag node in input is either MVT::v2i64 or
MVT::v2f64 (and we have SSE2), then try to fold according to rules:

  3) fold (vselect (build_vector (0, -1)), A, B) -> (movsd A, B)
  4) fold (vselect (build_vector (-1, 0)), A, B) -> (movsd B, A)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@199683 91177308-0d34-0410-b5e6-96231b3b80d8
2014-01-20 19:35:22 +00:00

105 lines
3.0 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
; AVX128 tests:
;CHECK-LABEL: vsel_float:
;CHECK: vblendvps
;CHECK: ret
define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x float> %v1, <4 x float> %v2
ret <4 x float> %vsel
}
;CHECK-LABEL: vsel_i32:
;CHECK: vblendvps
;CHECK: ret
define <4 x i32> @vsel_i32(<4 x i32> %v1, <4 x i32> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 true, i1 false>, <4 x i32> %v1, <4 x i32> %v2
ret <4 x i32> %vsel
}
;CHECK-LABEL: vsel_double:
;CHECK: vmovsd
;CHECK: ret
define <2 x double> @vsel_double(<2 x double> %v1, <2 x double> %v2) {
%vsel = select <2 x i1> <i1 true, i1 false>, <2 x double> %v1, <2 x double> %v2
ret <2 x double> %vsel
}
;CHECK-LABEL: vsel_i64:
;CHECK: vmovsd
;CHECK: ret
define <2 x i64> @vsel_i64(<2 x i64> %v1, <2 x i64> %v2) {
%vsel = select <2 x i1> <i1 true, i1 false>, <2 x i64> %v1, <2 x i64> %v2
ret <2 x i64> %vsel
}
;CHECK-LABEL: vsel_i8:
;CHECK: vpblendvb
;CHECK: ret
define <16 x i8> @vsel_i8(<16 x i8> %v1, <16 x i8> %v2) {
%vsel = select <16 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <16 x i8> %v1, <16 x i8> %v2
ret <16 x i8> %vsel
}
; AVX256 tests:
;CHECK-LABEL: vsel_float8:
;CHECK: vblendvps
;CHECK: ret
define <8 x float> @vsel_float8(<8 x float> %v1, <8 x float> %v2) {
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x float> %v1, <8 x float> %v2
ret <8 x float> %vsel
}
;CHECK-LABEL: vsel_i328:
;CHECK: vblendvps
;CHECK: ret
define <8 x i32> @vsel_i328(<8 x i32> %v1, <8 x i32> %v2) {
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x i32> %v1, <8 x i32> %v2
ret <8 x i32> %vsel
}
;CHECK-LABEL: vsel_double8:
;CHECK: vblendvpd
;CHECK: ret
define <8 x double> @vsel_double8(<8 x double> %v1, <8 x double> %v2) {
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x double> %v1, <8 x double> %v2
ret <8 x double> %vsel
}
;CHECK-LABEL: vsel_i648:
;CHECK: vblendvpd
;CHECK: ret
define <8 x i64> @vsel_i648(<8 x i64> %v1, <8 x i64> %v2) {
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x i64> %v1, <8 x i64> %v2
ret <8 x i64> %vsel
}
;; TEST blend + compares
; CHECK: testa
define <2 x double> @testa(<2 x double> %x, <2 x double> %y) {
; CHECK: vcmplepd
; CHECK: vblendvpd
%max_is_x = fcmp oge <2 x double> %x, %y
%max = select <2 x i1> %max_is_x, <2 x double> %x, <2 x double> %y
ret <2 x double> %max
}
; CHECK: testb
define <2 x double> @testb(<2 x double> %x, <2 x double> %y) {
; CHECK: vcmpnlepd
; CHECK: vblendvpd
%min_is_x = fcmp ult <2 x double> %x, %y
%min = select <2 x i1> %min_is_x, <2 x double> %x, <2 x double> %y
ret <2 x double> %min
}