[llvm] 5c8760b - [AArch64] Update arith-fp.ll codegen test. NFC
David Green via llvm-commits
llvm-commits at lists.llvm.org
Tue Mar 11 05:51:04 PDT 2025
Author: David Green
Date: 2025-03-11T12:50:59Z
New Revision: 5c8760b1abb677d5eb65ed9a18521d0a6d5121cc
URL: https://github.com/llvm/llvm-project/commit/5c8760b1abb677d5eb65ed9a18521d0a6d5121cc
DIFF: https://github.com/llvm/llvm-project/commit/5c8760b1abb677d5eb65ed9a18521d0a6d5121cc.diff
LOG: [AArch64] Update arith-fp.ll codegen test. NFC
A run line with and without +fullfp16 is added to check the differences between
the two, and the fp16 tests are separated out to keep the other check lines
simpler. FP128 tests are added for all operations, and fmuladd tests are added
similar to fma.
Added:
Modified:
llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
index de6b918afe943..1efd41426c4ef 100644
--- a/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/AArch64/arith-fp.ll
@@ -1,14 +1,11 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64 | FileCheck %s --check-prefixes=CHECK,CHECK-BASE
+; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64 -mattr=+fullfp16 | FileCheck %s --check-prefixes=CHECK,CHECK-FP16
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
-define i32 @fadd(i32 %arg) {
+define void @fadd() {
; CHECK-LABEL: 'fadd'
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fadd half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fadd <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fadd <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fadd <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fadd float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fadd <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fadd <4 x float> undef, undef
@@ -16,13 +13,10 @@ define i32 @fadd(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fadd double undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fadd <2 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fadd <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fadd fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F129 = fadd <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fadd half undef, undef
- %V4F16 = fadd <4 x half> undef, undef
- %V8F16 = fadd <8 x half> undef, undef
- %V16F16 = fadd <16 x half> undef, undef
-
%F32 = fadd float undef, undef
%V2F32 = fadd <2 x float> undef, undef
%V4F32 = fadd <4 x float> undef, undef
@@ -32,15 +26,36 @@ define i32 @fadd(i32 %arg) {
%V2F64 = fadd <2 x double> undef, undef
%V4F64 = fadd <4 x double> undef, undef
- ret i32 undef
+ %F128 = fadd fp128 undef, undef
+ %V2F129 = fadd <2 x fp128> undef, undef
+
+ ret void
+}
+
+define void @fadd_fp16() {
+; CHECK-BASE-LABEL: 'fadd_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fadd half undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fadd <4 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fadd <8 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fadd <16 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fadd_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fadd half undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fadd <4 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fadd <8 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fadd <16 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fadd half undef, undef
+ %V4F16 = fadd <4 x half> undef, undef
+ %V8F16 = fadd <8 x half> undef, undef
+ %V16F16 = fadd <16 x half> undef, undef
+ ret void
}
-define i32 @fsub(i32 %arg) {
+define void @fsub() {
; CHECK-LABEL: 'fsub'
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fsub <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fsub float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fsub <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fsub <4 x float> undef, undef
@@ -48,13 +63,10 @@ define i32 @fsub(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fsub double undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fsub <2 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fsub <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fsub fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F129 = fsub <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fsub half undef, undef
- %V4F16 = fsub <4 x half> undef, undef
- %V8F16 = fsub <8 x half> undef, undef
- %V16F16 = fsub <16 x half> undef, undef
-
%F32 = fsub float undef, undef
%V2F32 = fsub <2 x float> undef, undef
%V4F32 = fsub <4 x float> undef, undef
@@ -64,14 +76,36 @@ define i32 @fsub(i32 %arg) {
%V2F64 = fsub <2 x double> undef, undef
%V4F64 = fsub <4 x double> undef, undef
- ret i32 undef
+ %F128 = fsub fp128 undef, undef
+ %V2F129 = fsub <2 x fp128> undef, undef
+
+ ret void
}
-define i32 @fneg_idiom(i32 %arg) {
+define void @fsub_fp16() {
+; CHECK-BASE-LABEL: 'fsub_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fsub <16 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fsub_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fsub <16 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fsub half undef, undef
+ %V4F16 = fsub <4 x half> undef, undef
+ %V8F16 = fsub <8 x half> undef, undef
+ %V16F16 = fsub <16 x half> undef, undef
+ ret void
+}
+
+define void @fneg_idiom() {
; CHECK-LABEL: 'fneg_idiom'
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half 0xH8000, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fsub float -0.000000e+00, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fsub <2 x float> splat (float -0.000000e+00), undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fsub <4 x float> splat (float -0.000000e+00), undef
@@ -79,12 +113,10 @@ define i32 @fneg_idiom(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fsub double -0.000000e+00, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fsub <2 x double> splat (double -0.000000e+00), undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fsub <4 x double> splat (double -0.000000e+00), undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fsub fp128 0xL00000000000000008000000000000000, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F129 = fsub <2 x fp128> splat (fp128 0xL00000000000000008000000000000000), undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fsub half -0.0, undef
- %V4F16 = fsub <4 x half> <half -0.0, half -0.0, half -0.0, half -0.0>, undef
- %V8F16 = fsub <8 x half> <half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0>, undef
-
%F32 = fsub float -0.0, undef
%V2F32 = fsub <2 x float> <float -0.0, float -0.0>, undef
%V4F32 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, undef
@@ -94,16 +126,33 @@ define i32 @fneg_idiom(i32 %arg) {
%V2F64 = fsub <2 x double> <double -0.0, double -0.0>, undef
%V4F64 = fsub <4 x double> <double -0.0, double -0.0, double -0.0, double -0.0>, undef
- ret i32 undef
+ %F128 = fsub fp128 0xL00000000000000008000000000000000, undef
+ %V2F129 = fsub <2 x fp128> <fp128 0xL00000000000000008000000000000000, fp128 0xL00000000000000008000000000000000>, undef
+
+ ret void
}
-define i32 @fneg(i32 %arg) {
+define void @fneg_idiom_fp16() {
+; CHECK-BASE-LABEL: 'fneg_idiom_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half 0xH8000, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fneg_idiom_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fsub half 0xH8000, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fsub <4 x half> splat (half 0xH8000), undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fsub <8 x half> splat (half 0xH8000), undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fsub half -0.0, undef
+ %V4F16 = fsub <4 x half> <half -0.0, half -0.0, half -0.0, half -0.0>, undef
+ %V8F16 = fsub <8 x half> <half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0, half -0.0>, undef
+ ret void
+}
+
+define void @fneg() {
; CHECK-LABEL: 'fneg'
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fneg <2 x float> undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fneg <4 x float> undef
@@ -111,14 +160,10 @@ define i32 @fneg(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fneg double undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fneg <2 x double> undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fneg fp128 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V2F129 = fneg <2 x fp128> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fneg half undef
- %V2F16 = fneg <2 x half> undef
- %V4F16 = fneg <4 x half> undef
- %V8F16 = fneg <8 x half> undef
- %V16F16 = fneg <16 x half> undef
-
%F32 = fneg float undef
%V2F32 = fneg <2 x float> undef
%V4F32 = fneg <4 x float> undef
@@ -128,21 +173,39 @@ define i32 @fneg(i32 %arg) {
%V2F64 = fneg <2 x double> undef
%V4F64 = fneg <4 x double> undef
- ret i32 undef
+ %F128 = fneg fp128 undef
+ %V2F129 = fneg <2 x fp128> undef
+
+ ret void
}
-define i32 @fmulfneg(i32 %arg) {
+define void @fneg_fp16() {
+; CHECK-BASE-LABEL: 'fneg_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fneg_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fneg half undef
+ %V2F16 = fneg <2 x half> undef
+ %V4F16 = fneg <4 x half> undef
+ %V8F16 = fneg <8 x half> undef
+ %V16F16 = fneg <16 x half> undef
+ ret void
+}
+
+define void @fmulfneg() {
; CHECK-LABEL: 'fmulfneg'
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half %F16, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> %V2F16, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> %V4F16, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> %V8F16, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> %V16F16, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32M = fmul float %F32, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fneg <2 x float> undef
@@ -157,19 +220,12 @@ define i32 @fmulfneg(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64M = fmul <2 x double> %V2F64, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> undef
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64M = fmul <4 x double> %V4F64, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fneg fp128 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128M = fmul fp128 %F128, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V2F128 = fneg <2 x fp128> undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F128M = fmul <2 x fp128> %V2F128, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fneg half undef
- %F16M = fmul half %F16, undef
- %V2F16 = fneg <2 x half> undef
- %V2F16M = fmul <2 x half> %V2F16, undef
- %V4F16 = fneg <4 x half> undef
- %V4F16M = fmul <4 x half> %V4F16, undef
- %V8F16 = fneg <8 x half> undef
- %V8F16M = fmul <8 x half> %V8F16, undef
- %V16F16 = fneg <16 x half> undef
- %V16F16M = fmul <16 x half> %V16F16, undef
-
%F32 = fneg float undef
%F32M = fmul float %F32, undef
%V2F32 = fneg <2 x float> undef
@@ -186,21 +242,56 @@ define i32 @fmulfneg(i32 %arg) {
%V4F64 = fneg <4 x double> undef
%V4F64M = fmul <4 x double> %V4F64, undef
- ret i32 undef
+ %F128 = fneg fp128 undef
+ %F128M = fmul fp128 %F128, undef
+ %V2F128 = fneg <2 x fp128> undef
+ %V2F128M = fmul <2 x fp128> %V2F128, undef
+
+ ret void
+}
+
+define void @fmulneg_fp16() {
+; CHECK-BASE-LABEL: 'fmulneg_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half %F16, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> %V2F16, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> %V4F16, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> %V8F16, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> %V16F16, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fmulneg_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half %F16, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> %V2F16, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> %V4F16, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> %V8F16, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> %V16F16, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fneg half undef
+ %F16M = fmul half %F16, undef
+ %V2F16 = fneg <2 x half> undef
+ %V2F16M = fmul <2 x half> %V2F16, undef
+ %V4F16 = fneg <4 x half> undef
+ %V4F16M = fmul <4 x half> %V4F16, undef
+ %V8F16 = fneg <8 x half> undef
+ %V8F16M = fmul <8 x half> %V8F16, undef
+ %V16F16 = fneg <16 x half> undef
+ %V16F16M = fmul <16 x half> %V16F16, undef
+ ret void
}
-define i32 @fnegfmul(i32 %arg) {
+define void @fnegfmul() {
; CHECK-LABEL: 'fnegfmul'
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half %F16M
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> %V2F16M
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> %V4F16M
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> %V8F16M
-; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> %V16F16M
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32M = fmul float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fneg float %F32M
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32M = fmul <2 x float> undef, undef
@@ -215,19 +306,12 @@ define i32 @fnegfmul(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fneg <2 x double> %V2F64M
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64M = fmul <4 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fneg <4 x double> %V4F64M
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128M = fmul fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fneg fp128 %F128M
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F128M = fmul <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V2F128 = fneg <2 x fp128> %V2F128M
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16M = fmul half undef, undef
- %F16 = fneg half %F16M
- %V2F16M = fmul <2 x half> undef, undef
- %V2F16 = fneg <2 x half> %V2F16M
- %V4F16M = fmul <4 x half> undef, undef
- %V4F16 = fneg <4 x half> %V4F16M
- %V8F16M = fmul <8 x half> undef, undef
- %V8F16 = fneg <8 x half> %V8F16M
- %V16F16M = fmul <16 x half> undef, undef
- %V16F16 = fneg <16 x half> %V16F16M
-
%F32M = fmul float undef, undef
%F32 = fneg float %F32M
%V2F32M = fmul <2 x float> undef, undef
@@ -244,15 +328,56 @@ define i32 @fnegfmul(i32 %arg) {
%V4F64M = fmul <4 x double> undef, undef
%V4F64 = fneg <4 x double> %V4F64M
- ret i32 undef
+ %F128M = fmul fp128 undef, undef
+ %F128 = fneg fp128 %F128M
+ %V2F128M = fmul <2 x fp128> undef, undef
+ %V2F128 = fneg <2 x fp128> %V2F128M
+
+ ret void
+}
+
+define void @fnegfmul_fp16() {
+; CHECK-BASE-LABEL: 'fnegfmul_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half %F16M
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> %V2F16M
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> %V4F16M
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> %V8F16M
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> undef, undef
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> %V16F16M
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fnegfmul_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16M = fmul half undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fneg half %F16M
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16M = fmul <2 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V2F16 = fneg <2 x half> %V2F16M
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16M = fmul <4 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fneg <4 x half> %V4F16M
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16M = fmul <8 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:1 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fneg <8 x half> %V8F16M
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16M = fmul <16 x half> undef, undef
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fneg <16 x half> %V16F16M
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16M = fmul half undef, undef
+ %F16 = fneg half %F16M
+ %V2F16M = fmul <2 x half> undef, undef
+ %V2F16 = fneg <2 x half> %V2F16M
+ %V4F16M = fmul <4 x half> undef, undef
+ %V4F16 = fneg <4 x half> %V4F16M
+ %V8F16M = fmul <8 x half> undef, undef
+ %V8F16 = fneg <8 x half> %V8F16M
+ %V16F16M = fmul <16 x half> undef, undef
+ %V16F16 = fneg <16 x half> %V16F16M
+ ret void
}
-define i32 @fmul(i32 %arg) {
+define void @fmul() {
; CHECK-LABEL: 'fmul'
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fmul half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fmul <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fmul <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fmul <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F32 = fmul float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F32 = fmul <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F32 = fmul <4 x float> undef, undef
@@ -260,13 +385,10 @@ define i32 @fmul(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F64 = fmul double undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V2F64 = fmul <2 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V4F64 = fmul <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %F128 = fmul fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:1 Lat:3 SizeLat:1 for: %V2F128 = fmul <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fmul half undef, undef
- %V4F16 = fmul <4 x half> undef, undef
- %V8F16 = fmul <8 x half> undef, undef
- %V16F16 = fmul <16 x half> undef, undef
-
%F32 = fmul float undef, undef
%V2F32 = fmul <2 x float> undef, undef
%V4F32 = fmul <4 x float> undef, undef
@@ -276,15 +398,29 @@ define i32 @fmul(i32 %arg) {
%V2F64 = fmul <2 x double> undef, undef
%V4F64 = fmul <4 x double> undef, undef
- ret i32 undef
+ %F128 = fmul fp128 undef, undef
+ %V2F128 = fmul <2 x fp128> undef, undef
+
+ ret void
}
-define i32 @fdiv(i32 %arg) {
+define void @fmul_fp16() {
+; CHECK-LABEL: 'fmul_fp16'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %F16 = fmul half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V4F16 = fmul <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:1 Lat:3 SizeLat:1 for: %V8F16 = fmul <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:1 Lat:3 SizeLat:1 for: %V16F16 = fmul <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fmul half undef, undef
+ %V4F16 = fmul <4 x half> undef, undef
+ %V8F16 = fmul <8 x half> undef, undef
+ %V16F16 = fmul <16 x half> undef, undef
+ ret void
+}
+
+define void @fdiv() {
; CHECK-LABEL: 'fdiv'
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = fdiv half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = fdiv <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = fdiv <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = fdiv <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F32 = fdiv float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V2F32 = fdiv <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4F32 = fdiv <4 x float> undef, undef
@@ -292,13 +428,10 @@ define i32 @fdiv(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F64 = fdiv double undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V2F64 = fdiv <2 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = fdiv <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %F128 = fdiv fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:4 Lat:4 SizeLat:4 for: %V2F128 = fdiv <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = fdiv half undef, undef
- %V4F16 = fdiv <4 x half> undef, undef
- %V8F16 = fdiv <8 x half> undef, undef
- %V16F16 = fdiv <16 x half> undef, undef
-
%F32 = fdiv float undef, undef
%V2F32 = fdiv <2 x float> undef, undef
%V4F32 = fdiv <4 x float> undef, undef
@@ -308,15 +441,29 @@ define i32 @fdiv(i32 %arg) {
%V2F64 = fdiv <2 x double> undef, undef
%V4F64 = fdiv <4 x double> undef, undef
- ret i32 undef
+ %F128 = fdiv fp128 undef, undef
+ %V2F128 = fdiv <2 x fp128> undef, undef
+
+ ret void
}
-define i32 @frem(i32 %arg) {
+define void @fdiv_fp16() {
+; CHECK-LABEL: 'fdiv_fp16'
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = fdiv half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = fdiv <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:2 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = fdiv <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = fdiv <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = fdiv half undef, undef
+ %V4F16 = fdiv <4 x half> undef, undef
+ %V8F16 = fdiv <8 x half> undef, undef
+ %V16F16 = fdiv <16 x half> undef, undef
+ ret void
+}
+
+define void @frem() {
; CHECK-LABEL: 'frem'
-; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = frem half undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:52 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = frem <4 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:108 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = frem <8 x half> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:216 CodeSize:4 Lat:4 SizeLat:4 for: %V16F16 = frem <16 x half> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F32 = frem float undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V2F32 = frem <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:52 CodeSize:4 Lat:4 SizeLat:4 for: %V4F32 = frem <4 x float> undef, undef
@@ -324,13 +471,10 @@ define i32 @frem(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F64 = frem double undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:24 CodeSize:4 Lat:4 SizeLat:4 for: %V2F64 = frem <2 x double> undef, undef
; CHECK-NEXT: Cost Model: Found costs of RThru:48 CodeSize:4 Lat:4 SizeLat:4 for: %V4F64 = frem <4 x double> undef, undef
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F128 = frem fp128 undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:20 CodeSize:4 Lat:4 SizeLat:4 for: %V2F128 = frem <2 x fp128> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = frem half undef, undef
- %V4F16 = frem <4 x half> undef, undef
- %V8F16 = frem <8 x half> undef, undef
- %V16F16 = frem <16 x half> undef, undef
-
%F32 = frem float undef, undef
%V2F32 = frem <2 x float> undef, undef
%V4F32 = frem <4 x float> undef, undef
@@ -340,15 +484,29 @@ define i32 @frem(i32 %arg) {
%V2F64 = frem <2 x double> undef, undef
%V4F64 = frem <4 x double> undef, undef
- ret i32 undef
+ %F128 = frem fp128 undef, undef
+ %V2F128 = frem <2 x fp128> undef, undef
+
+ ret void
+}
+
+define void @frem_fp16() {
+; CHECK-LABEL: 'frem_fp16'
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:4 Lat:4 SizeLat:4 for: %F16 = frem half undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:52 CodeSize:4 Lat:4 SizeLat:4 for: %V4F16 = frem <4 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:108 CodeSize:4 Lat:4 SizeLat:4 for: %V8F16 = frem <8 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:216 CodeSize:4 Lat:4 SizeLat:4 for: %V16F16 = frem <16 x half> undef, undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = frem half undef, undef
+ %V4F16 = frem <4 x half> undef, undef
+ %V8F16 = frem <8 x half> undef, undef
+ %V16F16 = frem <16 x half> undef, undef
+ ret void
}
-define i32 @fsqrt(i32 %arg) {
+define void @fsqrt() {
; CHECK-LABEL: 'fsqrt'
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.sqrt.f16(half undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.sqrt.f32(float undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
@@ -356,13 +514,10 @@ define i32 @fsqrt(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.sqrt.f64(double undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:10 SizeLat:10 for: %F128 = call fp128 @llvm.sqrt.f128(fp128 undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:20 CodeSize:2 Lat:20 SizeLat:20 for: %V2F128 = call <2 x fp128> @llvm.sqrt.v2f128(<2 x fp128> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = call half @llvm.sqrt.f16(half undef)
- %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
- %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
- %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
-
%F32 = call float @llvm.sqrt.f32(float undef)
%V2F32 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
%V4F32 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
@@ -372,15 +527,36 @@ define i32 @fsqrt(i32 %arg) {
%V2F64 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
%V4F64 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
- ret i32 undef
+ %F128 = call fp128 @llvm.sqrt.fp128(fp128 undef)
+ %V2F128 = call <2 x fp128> @llvm.sqrt.v2fp128(<2 x fp128> undef)
+
+ ret void
+}
+
+define void @fsqrt_fp16() {
+; CHECK-BASE-LABEL: 'fsqrt_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.sqrt.f16(half undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 10 for: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 22 for: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 44 for: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fsqrt_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.sqrt.f16(half undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = call half @llvm.sqrt.f16(half undef)
+ %V4F16 = call <4 x half> @llvm.sqrt.v4f16(<4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.sqrt.v8f16(<8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.sqrt.v16f16(<16 x half> undef)
+ ret void
}
-define i32 @fabs(i32 %arg) {
+define void @fabs() {
; CHECK-LABEL: 'fabs'
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fabs.f16(half undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fabs.f32(float undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
@@ -388,13 +564,10 @@ define i32 @fabs(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fabs.f64(double undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:10 SizeLat:10 for: %F128 = call fp128 @llvm.fabs.f128(fp128 undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:20 CodeSize:2 Lat:20 SizeLat:20 for: %V2F128 = call <2 x fp128> @llvm.fabs.v2f128(<2 x fp128> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = call half @llvm.fabs.f16(half undef)
- %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
- %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
- %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
-
%F32 = call float @llvm.fabs.f32(float undef)
%V2F32 = call <2 x float> @llvm.fabs.v2f32(<2 x float> undef)
%V4F32 = call <4 x float> @llvm.fabs.v4f32(<4 x float> undef)
@@ -404,15 +577,29 @@ define i32 @fabs(i32 %arg) {
%V2F64 = call <2 x double> @llvm.fabs.v2f64(<2 x double> undef)
%V4F64 = call <4 x double> @llvm.fabs.v4f64(<4 x double> undef)
- ret i32 undef
+ %F128 = call fp128 @llvm.fabs.fp128(fp128 undef)
+ %V2F128 = call <2 x fp128> @llvm.fabs.v2fp128(<2 x fp128> undef)
+
+ ret void
+}
+
+define void @fabs_fp16() {
+; CHECK-LABEL: 'fabs_fp16'
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fabs.f16(half undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = call half @llvm.fabs.f16(half undef)
+ %V4F16 = call <4 x half> @llvm.fabs.v4f16(<4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.fabs.v8f16(<8 x half> undef)
+ %V2F16 = call <16 x half> @llvm.fabs.v16f16(<16 x half> undef)
+ ret void
}
-define i32 @fcopysign(i32 %arg) {
+define void @fcopysign() {
; CHECK-LABEL: 'fcopysign'
-; CHECK-NEXT: Cost Model: Found costs of 2 for: %F16 = call half @llvm.copysign.f16(half undef, half undef)
-; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %F32 = call float @llvm.copysign.f32(float undef, float undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
@@ -420,13 +607,10 @@ define i32 @fcopysign(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of 2 for: %F64 = call double @llvm.copysign.f64(double undef, double undef)
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:10 SizeLat:10 for: %F128 = call fp128 @llvm.copysign.f128(fp128 undef, fp128 undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:20 CodeSize:2 Lat:20 SizeLat:20 for: %V2F128 = call <2 x fp128> @llvm.copysign.v2f128(<2 x fp128> undef, <2 x fp128> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = call half @llvm.copysign.f16(half undef, half undef)
- %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
- %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
- %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
-
%F32 = call float @llvm.copysign.f32(float undef, float undef)
%V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
%V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
@@ -436,15 +620,36 @@ define i32 @fcopysign(i32 %arg) {
%V2F64 = call <2 x double> @llvm.copysign.v2f64(<2 x double> undef, <2 x double> undef)
%V4F64 = call <4 x double> @llvm.copysign.v4f64(<4 x double> undef, <4 x double> undef)
- ret i32 undef
+ %F128 = call fp128 @llvm.copysign.fp128(fp128 undef, fp128 undef)
+ %V2F128 = call <2 x fp128> @llvm.copysign.v2fp128(<2 x fp128> undef, <2 x fp128> undef)
+
+ ret void
}
-define i32 @fma(i32 %arg) {
+define void @fcopysign_fp16() {
+; CHECK-BASE-LABEL: 'fcopysign_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.copysign.f16(half undef, half undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 2 for: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fcopysign_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of 2 for: %F16 = call half @llvm.copysign.f16(half undef, half undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 2 for: %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 2 for: %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = call half @llvm.copysign.f16(half undef, half undef)
+ %V4F16 = call <4 x half> @llvm.copysign.v4f16(<4 x half> undef, <4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.copysign.v8f16(<8 x half> undef, <8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.copysign.v16f16(<16 x half> undef, <16 x half> undef)
+ ret void
+}
+
+define void @fma() {
; CHECK-LABEL: 'fma'
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
-; CHECK-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
@@ -452,13 +657,10 @@ define i32 @fma(i32 %arg) {
; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
-; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 undef
+; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:1 Lat:10 SizeLat:10 for: %F128 = call fp128 @llvm.fma.f128(fp128 undef, fp128 undef, fp128 undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:20 CodeSize:2 Lat:20 SizeLat:20 for: %V2F128 = call <2 x fp128> @llvm.fma.v2f128(<2 x fp128> undef, <2 x fp128> undef, <2 x fp128> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
- %F16 = call float @llvm.fma.f32(float undef, float undef, float undef)
- %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
- %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
- %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
-
%F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
%V2F32 = call <2 x float> @llvm.fma.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
%V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
@@ -468,61 +670,80 @@ define i32 @fma(i32 %arg) {
%V2F64 = call <2 x double> @llvm.fma.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
%V4F64 = call <4 x double> @llvm.fma.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
- ret i32 undef
+ %F128 = call fp128 @llvm.fma.fp128(fp128 undef, fp128 undef, fp128 undef)
+ %V2F128 = call <2 x fp128> @llvm.fma.v2fp128(<2 x fp128> undef, <2 x fp128> undef, <2 x fp128> undef)
+
+ ret void
+}
+
+define void @fma_fp16() {
+; CHECK-BASE-LABEL: 'fma_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fma.f16(half undef, half undef, half undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 10 for: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 22 for: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of 44 for: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fma_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fma.f16(half undef, half undef, half undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = call half @llvm.fma.f16(half undef, half undef, half undef)
+ %V4F16 = call <4 x half> @llvm.fma.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.fma.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.fma.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+ ret void
}
-declare half @llvm.sqrt.f16(half)
-declare <4 x half> @llvm.sqrt.v4f16(<4 x half>)
-declare <8 x half> @llvm.sqrt.v8f16(<8 x half>)
-declare <16 x half> @llvm.sqrt.v16f16(<16 x half>)
-
-declare float @llvm.sqrt.f32(float)
-declare <2 x float> @llvm.sqrt.v2f32(<2 x float>)
-declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
-declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
-
-declare double @llvm.sqrt.f64(double)
-declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
-declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
-
-declare half @llvm.fabs.f16(half)
-declare <4 x half> @llvm.fabs.v4f16(<4 x half>)
-declare <8 x half> @llvm.fabs.v8f16(<8 x half>)
-declare <16 x half> @llvm.fabs.v16f16(<16 x half>)
-
-declare float @llvm.fabs.f32(float)
-declare <2 x float> @llvm.fabs.v2f32(<2 x float>)
-declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
-declare <8 x float> @llvm.fabs.v8f32(<8 x float>)
-
-declare double @llvm.fabs.f64(double)
-declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
-declare <4 x double> @llvm.fabs.v4f64(<4 x double>)
-
-declare half @llvm.copysign.f16(half, half)
-declare <4 x half> @llvm.copysign.v4f16(<4 x half>, <4 x half>)
-declare <8 x half> @llvm.copysign.v8f16(<8 x half>, <8 x half>)
-declare <16 x half> @llvm.copysign.v16f16(<16 x half>, <16 x half>)
-
-declare float @llvm.copysign.f32(float, float)
-declare <2 x float> @llvm.copysign.v2f32(<2 x float>, <2 x float>)
-declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>)
-declare <8 x float> @llvm.copysign.v8f32(<8 x float>, <8 x float>)
-
-declare double @llvm.copysign.f64(double, double)
-declare <2 x double> @llvm.copysign.v2f64(<2 x double>, <2 x double>)
-declare <4 x double> @llvm.copysign.v4f64(<4 x double>, <4 x double>)
-
-declare half @llvm.fma.f16(half, half, half)
-declare <4 x half> @llvm.fma.v4f16(<4 x half>, <4 x half>, <4 x half>)
-declare <8 x half> @llvm.fma.v8f16(<8 x half>, <8 x half>, <8 x half>)
-declare <16 x half> @llvm.fma.v16f16(<16 x half>, <16 x half>, <16 x half>)
-
-declare float @llvm.fma.f32(float, float, float)
-declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>)
-declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
-declare <8 x float> @llvm.fma.v8f32(<8 x float>, <8 x float>, <8 x float>)
-
-declare double @llvm.fma.f64(double, double, double)
-declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
-declare <4 x double> @llvm.fma.v4f64(<4 x double>, <4 x double>, <4 x double>)
+define void @fmuladd() {
+; CHECK-LABEL: 'fmuladd'
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F32 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F32 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4F32 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8F32 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %F64 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2F64 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4F64 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:8 CodeSize:2 Lat:6 SizeLat:2 for: %F128 = call fp128 @llvm.fmuladd.f128(fp128 undef, fp128 undef, fp128 undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:16 CodeSize:2 Lat:6 SizeLat:2 for: %V2F128 = call <2 x fp128> @llvm.fmuladd.v2f128(<2 x fp128> undef, <2 x fp128> undef, <2 x fp128> undef)
+; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F32 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)
+ %V2F32 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+ %V4F32 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+ %V8F32 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+
+ %F64 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+ %V2F64 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+ %V4F64 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+
+ %F128 = call fp128 @llvm.fmuladd.f128(fp128 undef, fp128 undef, fp128 undef)
+ %V2F128 = call <2 x fp128> @llvm.fmuladd.v2f128(<2 x fp128> undef, <2 x fp128> undef, <2 x fp128> undef)
+
+ ret void
+}
+
+define void @fmuladd_fp16() {
+; CHECK-BASE-LABEL: 'fmuladd_fp16'
+; CHECK-BASE-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:6 SizeLat:2 for: %V4F16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:4 CodeSize:2 Lat:6 SizeLat:2 for: %V8F16 = call <8 x half> @llvm.fmuladd.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:8 CodeSize:2 Lat:6 SizeLat:2 for: %V16F16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-BASE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+; CHECK-FP16-LABEL: 'fmuladd_fp16'
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %F16 = call half @llvm.fmuladd.f16(half undef, half undef, half undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V4F16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 1 for: %V8F16 = call <8 x half> @llvm.fmuladd.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of 4 for: %V16F16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+; CHECK-FP16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
+;
+ %F16 = call half @llvm.fmuladd.f32(half undef, half undef, half undef)
+ %V4F16 = call <4 x half> @llvm.fmuladd.v4f16(<4 x half> undef, <4 x half> undef, <4 x half> undef)
+ %V8F16 = call <8 x half> @llvm.fmuladd.v8f16(<8 x half> undef, <8 x half> undef, <8 x half> undef)
+ %V16F16 = call <16 x half> @llvm.fmuladd.v16f16(<16 x half> undef, <16 x half> undef, <16 x half> undef)
+ ret void
+}
More information about the llvm-commits
mailing list