[llvm] cce1fa3 - [RISCV] Add zvfbfmin arithmetic cost model test coverage. NFC
Luke Lau via llvm-commits
llvm-commits at lists.llvm.org
Mon Sep 23 08:28:47 PDT 2024
Author: Luke Lau
Date: 2024-09-23T23:28:25+08:00
New Revision: cce1fa39eabfca4907ff8d616618683eec1a5486
URL: https://github.com/llvm/llvm-project/commit/cce1fa39eabfca4907ff8d616618683eec1a5486
DIFF: https://github.com/llvm/llvm-project/commit/cce1fa39eabfca4907ff8d616618683eec1a5486.diff
LOG: [RISCV] Add zvfbfmin arithmetic cost model test coverage. NFC
Added:
Modified:
llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
Removed:
################################################################################
diff --git a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
index ff2609b5cc4e0a..b96fdb0109829b 100644
--- a/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/arith-fp.ll
@@ -1,13 +1,24 @@
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfh < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
-; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfh,+zvfbfmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFH
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64 -mattr=+v,+f,+d,+zfh,+zvfhmin,+zvfbfmin < %s | FileCheck %s --check-prefixes=CHECK,ZVFHMIN
; Check that we don't crash querying costs when vectors are not enabled.
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=riscv64
define void @fadd() {
; CHECK-LABEL: 'fadd'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %BF16 = fadd bfloat undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fadd float undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fadd double undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = fadd <1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16 = fadd <2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fadd <4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fadd <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fadd <16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fadd <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fadd <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fadd <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fadd <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fadd <4 x float> undef, undef
@@ -28,9 +39,22 @@ define void @fadd() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fadd <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = fadd bfloat undef, undef
%F32 = fadd float undef, undef
%F64 = fadd double undef, undef
+ %V1BF16 = fadd <1 x bfloat> undef, undef
+ %V2BF16 = fadd <2 x bfloat> undef, undef
+ %V4BF16 = fadd <4 x bfloat> undef, undef
+ %V8BF16 = fadd <8 x bfloat> undef, undef
+ %V16BF16 = fadd <16 x bfloat> undef, undef
+
+ %NXV1BF16 = fadd <vscale x 1 x bfloat> undef, undef
+ %NXV2BF16 = fadd <vscale x 2 x bfloat> undef, undef
+ %NXV4BF16 = fadd <vscale x 4 x bfloat> undef, undef
+ %NXV8BF16 = fadd <vscale x 8 x bfloat> undef, undef
+ %NXV16BF16 = fadd <vscale x 16 x bfloat> undef, undef
+
%V1F32 = fadd <1 x float> undef, undef
%V2F32 = fadd <2 x float> undef, undef
%V4F32 = fadd <4 x float> undef, undef
@@ -94,8 +118,19 @@ define void @fadd_f16() {
define void @fsub() {
; CHECK-LABEL: 'fsub'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F16 = fsub half undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fsub float undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fsub double undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = fsub <1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16 = fsub <2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fsub <4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fsub <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fsub <16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fsub <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fsub <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fsub <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fsub <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fsub <4 x float> undef, undef
@@ -116,9 +151,22 @@ define void @fsub() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fsub <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %F16 = fsub half undef, undef
%F32 = fsub float undef, undef
%F64 = fsub double undef, undef
+ %V1BF16 = fsub <1 x bfloat> undef, undef
+ %V2BF16 = fsub <2 x bfloat> undef, undef
+ %V4BF16 = fsub <4 x bfloat> undef, undef
+ %V8BF16 = fsub <8 x bfloat> undef, undef
+ %V16BF16 = fsub <16 x bfloat> undef, undef
+
+ %NXV1BF16 = fsub <vscale x 1 x bfloat> undef, undef
+ %NXV2BF16 = fsub <vscale x 2 x bfloat> undef, undef
+ %NXV4BF16 = fsub <vscale x 4 x bfloat> undef, undef
+ %NXV8BF16 = fsub <vscale x 8 x bfloat> undef, undef
+ %NXV16BF16 = fsub <vscale x 16 x bfloat> undef, undef
+
%V1F32 = fsub <1 x float> undef, undef
%V2F32 = fsub <2 x float> undef, undef
%V4F32 = fsub <4 x float> undef, undef
@@ -182,8 +230,19 @@ define void @fsub_f16() {
define void @fmul() {
; CHECK-LABEL: 'fmul'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %BF16 = fmul bfloat undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fmul float undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fmul double undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = fmul <1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16 = fmul <2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fmul <4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fmul <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fmul <16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fmul <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fmul <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fmul <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fmul <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fmul <4 x float> undef, undef
@@ -204,9 +263,22 @@ define void @fmul() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fmul <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = fmul bfloat undef, undef
%F32 = fmul float undef, undef
%F64 = fmul double undef, undef
+ %V1BF16 = fmul <1 x bfloat> undef, undef
+ %V2BF16 = fmul <2 x bfloat> undef, undef
+ %V4BF16 = fmul <4 x bfloat> undef, undef
+ %V8BF16 = fmul <8 x bfloat> undef, undef
+ %V16BF16 = fmul <16 x bfloat> undef, undef
+
+ %NXV1BF16 = fmul <vscale x 1 x bfloat> undef, undef
+ %NXV2BF16 = fmul <vscale x 2 x bfloat> undef, undef
+ %NXV4BF16 = fmul <vscale x 4 x bfloat> undef, undef
+ %NXV8BF16 = fmul <vscale x 8 x bfloat> undef, undef
+ %NXV16BF16 = fmul <vscale x 16 x bfloat> undef, undef
+
%V1F32 = fmul <1 x float> undef, undef
%V2F32 = fmul <2 x float> undef, undef
%V4F32 = fmul <4 x float> undef, undef
@@ -270,8 +342,19 @@ define void @fmul_f16() {
define void @fdiv() {
; CHECK-LABEL: 'fdiv'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %BF16 = fdiv bfloat undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fdiv float undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fdiv double undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = fdiv <1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16 = fdiv <2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fdiv <4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fdiv <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fdiv <16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fdiv <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fdiv <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fdiv <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fdiv <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fdiv <4 x float> undef, undef
@@ -292,9 +375,22 @@ define void @fdiv() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fdiv <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = fdiv bfloat undef, undef
%F32 = fdiv float undef, undef
%F64 = fdiv double undef, undef
+ %V1BF16 = fdiv <1 x bfloat> undef, undef
+ %V2BF16 = fdiv <2 x bfloat> undef, undef
+ %V4BF16 = fdiv <4 x bfloat> undef, undef
+ %V8BF16 = fdiv <8 x bfloat> undef, undef
+ %V16BF16 = fdiv <16 x bfloat> undef, undef
+
+ %NXV1BF16 = fdiv <vscale x 1 x bfloat> undef, undef
+ %NXV2BF16 = fdiv <vscale x 2 x bfloat> undef, undef
+ %NXV4BF16 = fdiv <vscale x 4 x bfloat> undef, undef
+ %NXV8BF16 = fdiv <vscale x 8 x bfloat> undef, undef
+ %NXV16BF16 = fdiv <vscale x 16 x bfloat> undef, undef
+
%V1F32 = fdiv <1 x float> undef, undef
%V2F32 = fdiv <2 x float> undef, undef
%V4F32 = fdiv <4 x float> undef, undef
@@ -358,8 +454,19 @@ define void @fdiv_f16() {
define void @frem() {
; CHECK-LABEL: 'frem'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %BF16 = frem bfloat undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = frem float undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = frem double undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = frem <1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2BF16 = frem <2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4BF16 = frem <4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 24 for instruction: %V8BF16 = frem <8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 63 for instruction: %V16BF16 = frem <16 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = frem <vscale x 1 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = frem <vscale x 2 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = frem <vscale x 4 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV8BF16 = frem <vscale x 8 x bfloat> undef, undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV16BF16 = frem <vscale x 16 x bfloat> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1F32 = frem <1 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = frem <2 x float> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %V4F32 = frem <4 x float> undef, undef
@@ -380,9 +487,22 @@ define void @frem() {
; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV8F64 = frem <vscale x 8 x double> undef, undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = frem bfloat undef, undef
%F32 = frem float undef, undef
%F64 = frem double undef, undef
+ %V1BF16 = frem <1 x bfloat> undef, undef
+ %V2BF16 = frem <2 x bfloat> undef, undef
+ %V4BF16 = frem <4 x bfloat> undef, undef
+ %V8BF16 = frem <8 x bfloat> undef, undef
+ %V16BF16 = frem <16 x bfloat> undef, undef
+
+ %NXV1BF16 = frem <vscale x 1 x bfloat> undef, undef
+ %NXV2BF16 = frem <vscale x 2 x bfloat> undef, undef
+ %NXV4BF16 = frem <vscale x 4 x bfloat> undef, undef
+ %NXV8BF16 = frem <vscale x 8 x bfloat> undef, undef
+ %NXV16BF16 = frem <vscale x 16 x bfloat> undef, undef
+
%V1F32 = frem <1 x float> undef, undef
%V2F32 = frem <2 x float> undef, undef
%V4F32 = frem <4 x float> undef, undef
@@ -462,8 +582,19 @@ define void @frem_f16() {
define void @fneg() {
; CHECK-LABEL: 'fneg'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %BF16 = fneg half undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F32 = fneg float undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %F64 = fneg double undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1BF16 = fneg <1 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2BF16 = fneg <2 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4BF16 = fneg <4 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8BF16 = fneg <8 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V16BF16 = fneg <16 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV1BF16 = fneg <vscale x 1 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV2BF16 = fneg <vscale x 2 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %NXV4BF16 = fneg <vscale x 4 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %NXV8BF16 = fneg <vscale x 8 x bfloat> undef
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %NXV16BF16 = fneg <vscale x 16 x bfloat> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = fneg <1 x float> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = fneg <2 x float> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = fneg <4 x float> undef
@@ -484,9 +615,22 @@ define void @fneg() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %NXV8F64 = fneg <vscale x 8 x double> undef
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = fneg half undef
%F32 = fneg float undef
%F64 = fneg double undef
+ %V1BF16 = fneg <1 x bfloat> undef
+ %V2BF16 = fneg <2 x bfloat> undef
+ %V4BF16 = fneg <4 x bfloat> undef
+ %V8BF16 = fneg <8 x bfloat> undef
+ %V16BF16 = fneg <16 x bfloat> undef
+
+ %NXV1BF16 = fneg <vscale x 1 x bfloat> undef
+ %NXV2BF16 = fneg <vscale x 2 x bfloat> undef
+ %NXV4BF16 = fneg <vscale x 4 x bfloat> undef
+ %NXV8BF16 = fneg <vscale x 8 x bfloat> undef
+ %NXV16BF16 = fneg <vscale x 16 x bfloat> undef
+
%V1F32 = fneg <1 x float> undef
%V2F32 = fneg <2 x float> undef
%V4F32 = fneg <4 x float> undef
@@ -550,8 +694,19 @@ define void @fneg_f16() {
define void @fcopysign() {
; CHECK-LABEL: 'fcopysign'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %BF16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.copysign.f32(float undef, float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.copysign.f64(double undef, double undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1BF16 = call <1 x bfloat> @llvm.copysign.v1bf16(<1 x bfloat> undef, <1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V16BF16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV1BF16 = call <vscale x 1 x bfloat> @llvm.copysign.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV2BF16 = call <vscale x 2 x bfloat> @llvm.copysign.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV4BF16 = call <vscale x 4 x bfloat> @llvm.copysign.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV8BF16 = call <vscale x 8 x bfloat> @llvm.copysign.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Invalid cost for instruction: %NXV16BF16 = call <vscale x 16 x bfloat> @llvm.copysign.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.copysign.v1f32(<1 x float> undef, <1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2F32 = call <2 x float> @llvm.copysign.v2f32(<2 x float> undef, <2 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.copysign.v4f32(<4 x float> undef, <4 x float> undef)
@@ -572,9 +727,22 @@ define void @fcopysign() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV8F64 = call <vscale x 8 x double> @llvm.copysign.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = call bfloat @llvm.copysign.bf16(bfloat undef, bfloat undef)
%F32 = call float @llvm.copysign.f32(float undef, float undef)
%F64 = call double @llvm.copysign.f64(double undef, double undef)
+ %V1BF16 = call <1 x bfloat> @llvm.copysign.v1bf16(<1 x bfloat> undef, <1 x bfloat> undef)
+ %V2BF16 = call <2 x bfloat> @llvm.copysign.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef)
+ %V4BF16 = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef)
+ %V8BF16 = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef)
+ %V16BF16 = call <16 x bfloat> @llvm.copysign.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef)
+
+ %NXV1BF16 = call <vscale x 1 x bfloat> @llvm.copysign.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+ %NXV2BF16 = call <vscale x 2 x bfloat> @llvm.copysign.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+ %NXV4BF16 = call <vscale x 4 x bfloat> @llvm.copysign.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+ %NXV8BF16 = call <vscale x 8 x bfloat> @llvm.copysign.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+ %NXV16BF16 = call <vscale x 16 x bfloat> @llvm.copysign.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
+
%V1F32 = call <1 x float> @llvm.copysign.v1f32(<1 x float> undef, <1 x 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)
@@ -654,8 +822,19 @@ define void @fcopysign_f16() {
define void @fma() {
; CHECK-LABEL: 'fma'
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %BF16 = call bfloat @llvm.fma.bf16(bfloat undef, bfloat undef, bfloat undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1BF16 = call <1 x bfloat> @llvm.fma.v1bf16(<1 x bfloat> undef, <1 x bfloat> undef, <1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V2BF16 = call <2 x bfloat> @llvm.fma.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V4BF16 = call <4 x bfloat> @llvm.fma.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 16 for instruction: %V8BF16 = call <8 x bfloat> @llvm.fma.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef, <8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 47 for instruction: %V16BF16 = call <16 x bfloat> @llvm.fma.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV1BF16 = call <vscale x 1 x bfloat> @llvm.fma.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV2BF16 = call <vscale x 2 x bfloat> @llvm.fma.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV4BF16 = call <vscale x 4 x bfloat> @llvm.fma.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV8BF16 = call <vscale x 8 x bfloat> @llvm.fma.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV16BF16 = call <vscale x 16 x bfloat> @llvm.fma.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1F32 = call <1 x float> @llvm.fma.v1f32(<1 x float> undef, <1 x float> undef, <1 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %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 an estimated cost of 2 for instruction: %V4F32 = call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
@@ -676,9 +855,22 @@ define void @fma() {
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %NXV8F64 = call <vscale x 8 x double> @llvm.fma.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ %BF16 = call bfloat @llvm.fma.bf16(bfloat undef, bfloat undef, bfloat undef)
%F32 = call float @llvm.fma.f32(float undef, float undef, float undef)
%F64 = call double @llvm.fma.f64(double undef, double undef, double undef)
+ %V1BF16 = call <1 x bfloat> @llvm.fma.v1bf16(<1 x bfloat> undef, <1 x bfloat> undef, <1 x bfloat> undef)
+ %V2BF16 = call <2 x bfloat> @llvm.fma.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)
+ %V4BF16 = call <4 x bfloat> @llvm.fma.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)
+ %V8BF16 = call <8 x bfloat> @llvm.fma.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef, <8 x bfloat> undef)
+ %V16BF16 = call <16 x bfloat> @llvm.fma.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)
+
+ %NXV1BF16 = call <vscale x 1 x bfloat> @llvm.fma.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+ %NXV2BF16 = call <vscale x 2 x bfloat> @llvm.fma.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+ %NXV4BF16 = call <vscale x 4 x bfloat> @llvm.fma.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+ %NXV8BF16 = call <vscale x 8 x bfloat> @llvm.fma.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+ %NXV16BF16 = call <vscale x 16 x bfloat> @llvm.fma.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
+
%V1F32 = call <1 x float> @llvm.fma.v1f32(<1 x float> undef, <1 x float> undef, <1 x 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)
@@ -758,30 +950,45 @@ define void @fma_f16() {
define void @fmuladd() {
; CHECK-LABEL: 'fmuladd'
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %3 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %5 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %7 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %14 = call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x double> @llvm.fmuladd.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
-; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %20 = call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %2 = call float @llvm.fmuladd.f32(float undef, float undef, float undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %4 = call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %5 = call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %6 = call <8 x bfloat> @llvm.fmuladd.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef, <8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %7 = call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %9 = call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %11 = call <16 x float> @llvm.fmuladd.v16f32(<16 x float> undef, <16 x float> undef, <16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %12 = call <2 x double> @llvm.fmuladd.v2f64(<2 x double> undef, <2 x double> undef, <2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %13 = call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %15 = call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 1 x bfloat> @llvm.fmuladd.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 2 x bfloat> @llvm.fmuladd.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 4 x bfloat> @llvm.fmuladd.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %19 = call <vscale x 8 x bfloat> @llvm.fmuladd.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <vscale x 16 x bfloat> @llvm.fmuladd.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %23 = call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <vscale x 8 x float> @llvm.fmuladd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <vscale x 16 x float> @llvm.fmuladd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x float> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x double> @llvm.fmuladd.nxv1f64(<vscale x 1 x double> undef, <vscale x 1 x double> undef, <vscale x 1 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x double> @llvm.fmuladd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %28 = call <vscale x 4 x double> @llvm.fmuladd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %29 = call <vscale x 8 x double> @llvm.fmuladd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x double> undef)
+; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %30 = call <vscale x 16 x double> @llvm.fmuladd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
+ call bfloat @llvm.fmuladd.bf16(bfloat undef, bfloat undef, bfloat undef)
call float @llvm.fmuladd.f32(float undef, float undef, float undef)
call double @llvm.fmuladd.f64(double undef, double undef, double undef)
+ call <2 x bfloat> @llvm.fmuladd.v2bf16(<2 x bfloat> undef, <2 x bfloat> undef, <2 x bfloat> undef)
+ call <4 x bfloat> @llvm.fmuladd.v4bf16(<4 x bfloat> undef, <4 x bfloat> undef, <4 x bfloat> undef)
+ call <8 x bfloat> @llvm.fmuladd.v8bf16(<8 x bfloat> undef, <8 x bfloat> undef, <8 x bfloat> undef)
+ call <16 x bfloat> @llvm.fmuladd.v16bf16(<16 x bfloat> undef, <16 x bfloat> undef, <16 x bfloat> undef)
call <2 x float> @llvm.fmuladd.v2f32(<2 x float> undef, <2 x float> undef, <2 x float> undef)
call <4 x float> @llvm.fmuladd.v4f32(<4 x float> undef, <4 x float> undef, <4 x float> undef)
call <8 x float> @llvm.fmuladd.v8f32(<8 x float> undef, <8 x float> undef, <8 x float> undef)
@@ -790,6 +997,11 @@ define void @fmuladd() {
call <4 x double> @llvm.fmuladd.v4f64(<4 x double> undef, <4 x double> undef, <4 x double> undef)
call <8 x double> @llvm.fmuladd.v8f64(<8 x double> undef, <8 x double> undef, <8 x double> undef)
call <16 x double> @llvm.fmuladd.v16f64(<16 x double> undef, <16 x double> undef, <16 x double> undef)
+ call <vscale x 1 x bfloat> @llvm.fmuladd.nxv1bf16(<vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef, <vscale x 1 x bfloat> undef)
+ call <vscale x 2 x bfloat> @llvm.fmuladd.nxv2bf16(<vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef, <vscale x 2 x bfloat> undef)
+ call <vscale x 4 x bfloat> @llvm.fmuladd.nxv4bf16(<vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef, <vscale x 4 x bfloat> undef)
+ call <vscale x 8 x bfloat> @llvm.fmuladd.nxv8bf16(<vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef, <vscale x 8 x bfloat> undef)
+ call <vscale x 16 x bfloat> @llvm.fmuladd.nxv16bf16(<vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef, <vscale x 16 x bfloat> undef)
call <vscale x 1 x float> @llvm.fmuladd.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef, <vscale x 1 x float> undef)
call <vscale x 2 x float> @llvm.fmuladd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x float> undef)
call <vscale x 4 x float> @llvm.fmuladd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
More information about the llvm-commits
mailing list