e430984ac4
* Encode vselect using BLEND instructions on x86 * Legalize vselect to bitselect * Optimize bitselect to vselect for some operands * Add run tests for bitselect-vselect optimization * Address review feedback
51 lines
1.4 KiB
Plaintext
51 lines
1.4 KiB
Plaintext
test simple_preopt
|
|
target x86_64
|
|
|
|
;; Test replacement of bitselect with vselect for special masks
|
|
|
|
function %mask_from_icmp(i8x16, i8x16) -> i8x16 {
|
|
block0(v0: i8x16, v1: i8x16):
|
|
v2 = icmp eq v0, v1
|
|
v3 = raw_bitcast.i8x16 v2
|
|
v4 = bitselect v3, v0, v1
|
|
; check: v4 = vselect v2, v0, v1
|
|
return v4
|
|
}
|
|
|
|
function %mask_casted(i8x16, i8x16, i32x4) -> i8x16 {
|
|
block0(v0: i8x16, v1: i8x16, v2: i32x4):
|
|
v3 = raw_bitcast.i8x16 v2
|
|
v4 = bitselect v3, v0, v1
|
|
; check: v4 = bitselect v3, v0, v1
|
|
return v4
|
|
}
|
|
|
|
function %good_const_mask_i8x16(i8x16, i8x16) -> i8x16 {
|
|
block0(v0: i8x16, v1: i8x16):
|
|
v3 = vconst.i8x16 [0 0 0xFF 0 0 0xFF 0 0 0 0 0xFF 0 0 0 0 0xFF]
|
|
v4 = bitselect v3, v0, v1
|
|
; check: v5 = raw_bitcast.b8x16 v3
|
|
; nextln: v4 = vselect v5, v0, v1
|
|
return v4
|
|
}
|
|
|
|
function %good_const_mask_i16x8(i16x8, i16x8) -> i16x8 {
|
|
block0(v0: i16x8, v1: i16x8):
|
|
v3 = vconst.i16x8 [0x0000 0xFF00 0x0000 0x00FF 0x0000 0xFFFF 0x00FF 0xFFFF]
|
|
v4 = bitselect v3, v0, v1
|
|
; check: v5 = raw_bitcast.b8x16 v3
|
|
; nextln: v6 = raw_bitcast.i8x16 v0
|
|
; nextln: v7 = raw_bitcast.i8x16 v1
|
|
; nextln: v8 = vselect v5, v6, v7
|
|
; nextln: v4 = raw_bitcast.i16x8 v8
|
|
return v4
|
|
}
|
|
|
|
function %bad_const_mask(i8x16, i8x16) -> i8x16 {
|
|
block0(v0: i8x16, v1: i8x16):
|
|
v3 = vconst.i8x16 [0 0 0xF0 0 0 0xFF 0 0 0 0 0xFF 0 0 0 0 0xFF]
|
|
v4 = bitselect v3, v0, v1
|
|
; check: v4 = bitselect v3, v0, v1
|
|
return v4
|
|
}
|