[AArch64] Add float vector compare/select cost-model tests.

This commit is contained in:
Florian Hahn 2022-01-26 16:26:19 +00:00
parent dcd0926ad0
commit e6ebd2c72d
No known key found for this signature in database
GPG Key ID: EEF712BB5E80EBBA
1 changed files with 571 additions and 2 deletions

View File

@ -1,5 +1,6 @@
; RUN: opt < %s -mtriple=aarch64--linux-gnu -cost-model -analyze | FileCheck %s --check-prefix=COST
; RUN: llc < %s -mtriple=aarch64--linux-gnu | FileCheck %s --check-prefix=CODE
; RUN: opt < %s -mtriple=aarch64--linux-gnu -cost-model -analyze | FileCheck %s --check-prefixes=COST,COST-NOFP16
; RUN: opt < %s -mtriple=aarch64--linux-gnu -cost-model -analyze -mattr=+fullfp16 | FileCheck %s --check-prefixes=COST,COST-FULLFP16
; RUN: llc < %s -mtriple=aarch64--linux-gnu -mattr=+fullfp16 | FileCheck %s --check-prefix=CODE
; COST-LABEL: v8i8_select_eq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = icmp eq <8 x i8> %a, %b
@ -151,3 +152,571 @@ define <2 x i64> @v2i64_select_no_cmp(<2 x i64> %a, <2 x i64> %b, <2 x i1> %cond
%s.1 = select <2 x i1> %cond, <2 x i64> %a, <2 x i64> %b
ret <2 x i64> %s.1
}
define <4 x half> @v4f16_select_ogt(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_ogt
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp ogt <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_ogt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ogt <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_ogt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_ogt
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp ogt <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_ogt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ogt <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_ogt(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_ogt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ogt <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_ogt(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_ogt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ogt <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_ogt(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_ogt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ogt <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_ogt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ogt <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <4 x half> @v4f16_select_oge(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_oge
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp oge <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_oge
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oge <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_oge(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_oge
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp oge <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_oge
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oge <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_oge(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_oge
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oge <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_oge(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_oge
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oge <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_oge(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_oge
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oge <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_oge
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oge <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <4 x half> @v4f16_select_olt(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_olt
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp olt <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_olt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp olt <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_olt(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_olt
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp olt <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_olt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp olt <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_olt(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_olt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp olt <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_olt(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_olt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp olt <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_olt(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_olt
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp olt <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_olt
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp olt <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <4 x half> @v4f16_select_ole(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_ole
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp ole <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_ole
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ole <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_ole(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_ole
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp ole <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_ole
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ole <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_ole(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_ole
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ole <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_ole(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_ole
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ole <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_ole(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_ole
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ole <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_ole
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ole <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <4 x half> @v4f16_select_oeq(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_oeq
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp oeq <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_oeq
; CODE: bb.0
; CODE-NEXT: fcmeq v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oeq <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_oeq(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_oeq
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp oeq <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_oeq
; CODE: bb.0
; CODE-NEXT: fcmeq v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oeq <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_oeq(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_oeq
; CODE: bb.0
; CODE-NEXT: fcmeq v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oeq <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_oeq(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
;
; CODE-LABEL: v4f32_select_oeq
; CODE: bb.0
; CODE-NEXT: fcmeq v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oeq <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_oeq(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_oeq
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp oeq <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_oeq
; CODE: bb.0
; CODE-NEXT: fcmeq v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp oeq <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <4 x half> @v4f16_select_one(<4 x half> %a, <4 x half> %b, <4 x half> %c) {
; COST-LABEL: v4f16_select_one
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cmp.1 = fcmp one <4 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp one <4 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
;
; CODE-LABEL: v4f16_select_one
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: fcmgt v{{.+}}.4h, v{{.+}}.4h, v{{.+}}.4h
; CODE-NEXT: orr v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp one <4 x half> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x half> %a, <4 x half> %c
ret <4 x half> %s.1
}
define <8 x half> @v8f16_select_one(<8 x half> %a, <8 x half> %b, <8 x half> %c) {
; COST-LABEL: v8f16_select_one
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %cmp.1 = fcmp one <8 x half> %a, %b
; COST-NOFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp one <8 x half> %a, %b
; COST-FULLFP16-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
;
; CODE-LABEL: v8f16_select_one
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: fcmgt v{{.+}}.8h, v{{.+}}.8h, v{{.+}}.8h
; CODE-NEXT: orr v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp one <8 x half> %a, %b
%s.1 = select <8 x i1> %cmp.1, <8 x half> %a, <8 x half> %c
ret <8 x half> %s.1
}
define <2 x float> @v2f32_select_one(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_one
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp one <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
; CODE-LABEL: v2f32_select_one
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: fcmgt v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: orr v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
%cmp.1 = fcmp one <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_one(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_one
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp one <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
; CODE-LABEL: v4f32_select_one
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: fcmgt v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: orr v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
%cmp.1 = fcmp one <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_one(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_one
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp one <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_one
; CODE: bb.0
; CODE-NEXT: fcmgt v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: fcmgt v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: orr v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp one <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}
define <2 x float> @v2f32_select_ord(<2 x float> %a, <2 x float> %b, <2 x float> %c) {
; COST-LABEL: v2f32_select_ord
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ord <2 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
;
; CODE-LABEL: v2f32_select_ord
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: fcmgt v{{.+}}.2s, v{{.+}}.2s, v{{.+}}.2s
; CODE-NEXT: orr v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: bif v{{.+}}.8b, v{{.+}}.8b, v{{.+}}.8b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ord <2 x float> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x float> %a, <2 x float> %c
ret <2 x float> %s.1
}
define <4 x float> @v4f32_select_ord(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; COST-LABEL: v4f32_select_ord
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ord <4 x float> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
; CODE-LABEL: v4f32_select_ord
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: fcmgt v{{.+}}.4s, v{{.+}}.4s, v{{.+}}.4s
; CODE-NEXT: orr v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
%cmp.1 = fcmp ord <4 x float> %a, %b
%s.1 = select <4 x i1> %cmp.1, <4 x float> %a, <4 x float> %c
ret <4 x float> %s.1
}
define <2 x double> @v2f64_select_ord(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; COST-LABEL: v2f64_select_ord
; COST-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cmp.1 = fcmp ord <2 x double> %a, %b
; COST-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
;
; CODE-LABEL: v2f64_select_ord
; CODE: bb.0
; CODE-NEXT: fcmge v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: fcmgt v{{.+}}.2d, v{{.+}}.2d, v{{.+}}.2d
; CODE-NEXT: orr v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: bif v{{.+}}.16b, v{{.+}}.16b, v{{.+}}.16b
; CODE-NEXT: ret
;
%cmp.1 = fcmp ord <2 x double> %a, %b
%s.1 = select <2 x i1> %cmp.1, <2 x double> %a, <2 x double> %c
ret <2 x double> %s.1
}