; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+sse4.2 -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,SSE,SSE42
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mattr=+avx2 -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
;
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skylake -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,AVX,SKL
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=knl -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,AVX512,KNL
; RUN: opt < %s -S -mtriple=x86_64-apple-darwin -mcpu=skx -cost-model -analyze | FileCheck %s --check-prefixes=CHECK,AVX512,SKX


define <2 x double> @test1(<2 x i64> %trigger, <2 x double>* %addr, <2 x double> %dst) {
; SSE2-LABEL: 'test1'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; SSE42-LABEL: 'test1'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX-LABEL: 'test1'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX512-LABEL: 'test1'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i64> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1> %mask, <2 x double> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
  %mask = icmp eq <2 x i64> %trigger, zeroinitializer
  %res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %addr, i32 4, <2 x i1>%mask, <2 x double>%dst)
  ret <2 x double> %res
}

define <4 x i32> @test2(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %dst) {
; SSE-LABEL: 'test2'
; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX-LABEL: 'test2'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX512-LABEL: 'test2'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1> %mask, <4 x i32> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %addr, i32 4, <4 x i1>%mask, <4 x i32>%dst)
  ret <4 x i32> %res
}

define void @test3(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
; SSE-LABEL: 'test3'
; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test3'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test3'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <4 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %val, <4 x i32>* %addr, i32 4, <4 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1>%mask)
  ret void
}

define <8 x float> @test4(<8 x i32> %trigger, <8 x float>* %addr, <8 x float> %dst) {
; SSE-LABEL: 'test4'
; SSE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; SSE-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX1-LABEL: 'test4'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX2-LABEL: 'test4'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX2-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; SKL-LABEL: 'test4'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
; AVX512-LABEL: 'test4'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <8 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1> %mask, <8 x float> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x float> %res
;
  %mask = icmp eq <8 x i32> %trigger, zeroinitializer
  %res = call <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>* %addr, i32 4, <8 x i1>%mask, <8 x float>%dst)
  ret <8 x float> %res
}

define void @test5(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %val) {
; SSE2-LABEL: 'test5'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'test5'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test5'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test5'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: call void @llvm.masked.store.v2f32.p0v2f32(<2 x float> %val, <2 x float>* %addr, i32 4, <2 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2f32.p0v2f32(<2 x float>%val, <2 x float>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define void @test6(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %val) {
; SSE2-LABEL: 'test6'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SSE42-LABEL: 'test6'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test6'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test6'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32> %val, <2 x i32>* %addr, i32 4, <2 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  call void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>%val, <2 x i32>* %addr, i32 4, <2 x i1>%mask)
  ret void
}

define <2 x float> @test7(<2 x i32> %trigger, <2 x float>* %addr, <2 x float> %dst) {
; SSE2-LABEL: 'test7'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; SSE42-LABEL: 'test7'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; AVX-LABEL: 'test7'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
; AVX512-LABEL: 'test7'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1> %mask, <2 x float> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x float> %res
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>%dst)
  ret <2 x float> %res
}

define <2 x i32> @test8(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
; SSE2-LABEL: 'test8'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; SSE42-LABEL: 'test8'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; AVX-LABEL: 'test8'
; AVX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
; AVX512-LABEL: 'test8'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %mask = icmp eq <2 x i32> %trigger, zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1> %mask, <2 x i32> %dst)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i32> %res
;
  %mask = icmp eq <2 x i32> %trigger, zeroinitializer
  %res = call <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
  ret <2 x i32> %res
}

define <2 x double> @test_gather_2f64(<2 x double*> %ptrs, <2 x i1> %mask, <2 x double> %src0)  {
; SSE-LABEL: 'test_gather_2f64'
; SSE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX1-LABEL: 'test_gather_2f64'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX2-LABEL: 'test_gather_2f64'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; SKL-LABEL: 'test_gather_2f64'
; SKL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;
; AVX512-LABEL: 'test_gather_2f64'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <2 x double> %res
;


%res = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32 4, <2 x i1> %mask, <2 x double> %src0)
  ret <2 x double> %res
}
declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)

define <4 x i32> @test_gather_4i32(<4 x i32*> %ptrs, <4 x i1> %mask, <4 x i32> %src0)  {
; SSE-LABEL: 'test_gather_4i32'
; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX1-LABEL: 'test_gather_4i32'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX2-LABEL: 'test_gather_4i32'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; SKL-LABEL: 'test_gather_4i32'
; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; KNL-LABEL: 'test_gather_4i32'
; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; SKX-LABEL: 'test_gather_4i32'
; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;


%res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> %src0)
  ret <4 x i32> %res
}

define <4 x i32> @test_gather_4i32_const_mask(<4 x i32*> %ptrs, <4 x i32> %src0)  {
; SSE-LABEL: 'test_gather_4i32_const_mask'
; SSE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX1-LABEL: 'test_gather_4i32_const_mask'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; AVX2-LABEL: 'test_gather_4i32_const_mask'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; SKL-LABEL: 'test_gather_4i32_const_mask'
; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; KNL-LABEL: 'test_gather_4i32_const_mask'
; KNL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;
; SKX-LABEL: 'test_gather_4i32_const_mask'
; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %res
;


%res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> %src0)
  ret <4 x i32> %res
}
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %ptrs, i32, <4 x i1> %mask, <4 x i32> %src0)

define <16 x float> @test_gather_16f32_const_mask(float* %base, <16 x i32> %ind) {
; SSE2-LABEL: 'test_gather_16f32_const_mask'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SSE42-LABEL: 'test_gather_16f32_const_mask'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX1-LABEL: 'test_gather_16f32_const_mask'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX2-LABEL: 'test_gather_16f32_const_mask'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SKL-LABEL: 'test_gather_16f32_const_mask'
; SKL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX512-LABEL: 'test_gather_16f32_const_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

define <16 x float> @test_gather_16f32_var_mask(float* %base, <16 x i32> %ind, <16 x i1>%mask) {
; SSE2-LABEL: 'test_gather_16f32_var_mask'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SSE42-LABEL: 'test_gather_16f32_var_mask'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX1-LABEL: 'test_gather_16f32_var_mask'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX2-LABEL: 'test_gather_16f32_var_mask'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SKL-LABEL: 'test_gather_16f32_var_mask'
; SKL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX512-LABEL: 'test_gather_16f32_var_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, float* %base, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
  ret <16 x float>%res
}

define <16 x float> @test_gather_16f32_ra_var_mask(<16 x float*> %ptrs, <16 x i32> %ind, <16 x i1>%mask) {
; SSE2-LABEL: 'test_gather_16f32_ra_var_mask'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SSE42-LABEL: 'test_gather_16f32_ra_var_mask'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 60 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX1-LABEL: 'test_gather_16f32_ra_var_mask'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX2-LABEL: 'test_gather_16f32_ra_var_mask'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 62 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SKL-LABEL: 'test_gather_16f32_ra_var_mask'
; SKL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX512-LABEL: 'test_gather_16f32_ra_var_mask'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 20 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.v = getelementptr float, <16 x float*> %ptrs, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32 4, <16 x i1> %mask, <16 x float> undef)
  ret <16 x float>%res
}

define <16 x float> @test_gather_16f32_const_mask2(float* %base, <16 x i32> %ind) {
; SSE2-LABEL: 'test_gather_16f32_const_mask2'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; SSE2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; SSE2-NEXT:  Cost Model: Found an estimated cost of 23 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SSE42-LABEL: 'test_gather_16f32_const_mask2'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; SSE42-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; SSE42-NEXT:  Cost Model: Found an estimated cost of 11 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 28 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX1-LABEL: 'test_gather_16f32_const_mask2'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; AVX1-NEXT:  Cost Model: Found an estimated cost of 19 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX2-LABEL: 'test_gather_16f32_const_mask2'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 30 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; SKL-LABEL: 'test_gather_16f32_const_mask2'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; SKL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
; AVX512-LABEL: 'test_gather_16f32_const_mask2'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %sext_ind = sext <16 x i32> %ind to <16 x i64>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <16 x float> %res
;
  %broadcast.splatinsert = insertelement <16 x float*> undef, float* %base, i32 0
  %broadcast.splat = shufflevector <16 x float*> %broadcast.splatinsert, <16 x float*> undef, <16 x i32> zeroinitializer

  %sext_ind = sext <16 x i32> %ind to <16 x i64>
  %gep.random = getelementptr float, <16 x float*> %broadcast.splat, <16 x i64> %sext_ind

  %res = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.random, i32 4, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x float> undef)
  ret <16 x float>%res
}

define void @test_scatter_16i32(i32* %base, <16 x i32> %ind, i16 %mask, <16 x i32>%val) {
; SSE-LABEL: 'test_scatter_16i32'
; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
; SSE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
; SSE-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX1-LABEL: 'test_scatter_16i32'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
; AVX1-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX2-LABEL: 'test_scatter_16i32'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SKL-LABEL: 'test_scatter_16i32'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %imask = bitcast i16 %mask to <16 x i1>
; SKL-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_scatter_16i32'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
; AVX512-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %imask = bitcast i16 %mask to <16 x i1>
; AVX512-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> %val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %broadcast.splatinsert = insertelement <16 x i32*> undef, i32* %base, i32 0
  %broadcast.splat = shufflevector <16 x i32*> %broadcast.splatinsert, <16 x i32*> undef, <16 x i32> zeroinitializer

  %gep.random = getelementptr i32, <16 x i32*> %broadcast.splat, <16 x i32> %ind
  %imask = bitcast i16 %mask to <16 x i1>
  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32 4, <16 x i1> %imask)
  ret void
}

define void @test_scatter_8i32(<8 x i32>%a1, <8 x i32*> %ptr, <8 x i1>%mask) {
; SSE-LABEL: 'test_scatter_8i32'
; SSE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test_scatter_8i32'
; AVX-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX512-LABEL: 'test_scatter_8i32'
; AVX512-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
; AVX512-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;

  call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32 4, <8 x i1> %mask)
  ret void
}

declare void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> %a1, <8 x i32*> %ptr, i32, <8 x i1> %mask)

define void @test_scatter_4i32(<4 x i32>%a1, <4 x i32*> %ptr, <4 x i1>%mask) {
; SSE-LABEL: 'test_scatter_4i32'
; SSE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
; SSE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; AVX-LABEL: 'test_scatter_4i32'
; AVX-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
; AVX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; KNL-LABEL: 'test_scatter_4i32'
; KNL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; SKX-LABEL: 'test_scatter_4i32'
; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32 4, <4 x i1> %mask)
  ret void
}

define <4 x float> @test_gather_4f32(float* %ptr, <4 x i32> %ind, <4 x i1>%mask) {
; SSE2-LABEL: 'test_gather_4f32'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SSE42-LABEL: 'test_gather_4f32'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; AVX1-LABEL: 'test_gather_4f32'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; AVX2-LABEL: 'test_gather_4f32'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SKL-LABEL: 'test_gather_4f32'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; KNL-LABEL: 'test_gather_4f32'
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; KNL-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SKX-LABEL: 'test_gather_4f32'
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
  %sext_ind = sext <4 x i32> %ind to <4 x i64>
  %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind

  %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> %mask, <4 x float> undef)
  ret <4 x float>%res
}

define <4 x float> @test_gather_4f32_const_mask(float* %ptr, <4 x i32> %ind) {
; SSE2-LABEL: 'test_gather_4f32_const_mask'
; SSE2-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SSE2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; SSE2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SSE42-LABEL: 'test_gather_4f32_const_mask'
; SSE42-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SSE42-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; SSE42-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; AVX1-LABEL: 'test_gather_4f32_const_mask'
; AVX1-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; AVX1-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; AVX1-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; AVX2-LABEL: 'test_gather_4f32_const_mask'
; AVX2-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; AVX2-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; AVX2-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SKL-LABEL: 'test_gather_4f32_const_mask'
; SKL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SKL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; SKL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; KNL-LABEL: 'test_gather_4f32_const_mask'
; KNL-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; KNL-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; KNL-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
; SKX-LABEL: 'test_gather_4f32_const_mask'
; SKX-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %sext_ind = sext <4 x i32> %ind to <4 x i64>
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind
; SKX-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
; SKX-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <4 x float> %res
;
  %sext_ind = sext <4 x i32> %ind to <4 x i64>
  %gep.v = getelementptr float, float* %ptr, <4 x i64> %sext_ind

  %res = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef)
  ret <4 x float>%res
}

declare <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep.v, i32, <4 x i1> %mask, <4 x float> )
declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %a1, <4 x i32*> %ptr, i32, <4 x i1> %mask)
declare void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>%val, <16 x i32*> %gep.random, i32, <16 x i1> %imask)
declare <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> %gep.v, i32, <16 x i1> %mask, <16 x float>)

declare <16 x i32> @llvm.masked.load.v16i32.p0v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
declare <2 x i32> @llvm.masked.load.v2i32.p0v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
declare void @llvm.masked.store.v16i32.p0v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
declare void @llvm.masked.store.v8i32.p0v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
declare void @llvm.masked.store.v2f32.p0v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)
declare void @llvm.masked.store.v2i32.p0v2i32(<2 x i32>, <2 x i32>*, i32, <2 x i1>)
declare void @llvm.masked.store.v16f32.p0v16f32(<16 x float>, <16 x float>*, i32, <16 x i1>)
declare <16 x float> @llvm.masked.load.v16f32.p0v16f32(<16 x float>*, i32, <16 x i1>, <16 x float>)
declare <8 x float> @llvm.masked.load.v8f32.p0v8f32(<8 x float>*, i32, <8 x i1>, <8 x float>)
declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32, <4 x i1>, <4 x float>)
declare <2 x float> @llvm.masked.load.v2f32.p0v2f32(<2 x float>*, i32, <2 x i1>, <2 x float>)
declare <8 x double> @llvm.masked.load.v8f64.p0v8f64(<8 x double>*, i32, <8 x i1>, <8 x double>)
declare <4 x double> @llvm.masked.load.v4f64.p0v4f64(<4 x double>*, i32, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>*, i32, <2 x i1>, <2 x double>)
declare void @llvm.masked.store.v8f64.p0v8f64(<8 x double>, <8 x double>*, i32, <8 x i1>)
declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double>, <2 x double>*, i32, <2 x i1>)
declare void @llvm.masked.store.v2i64.p0v2i64(<2 x i64>, <2 x i64>*, i32, <2 x i1>)