forked from OSchip/llvm-project
[SLP][AMDGPU] Regenerate packed-math tests and remove unused check prefix
This commit is contained in:
Simon Pilgrim
parent
a41d65aa5b
commit
b215adf4ed
|
|
@ -1,16 +1,21 @@
|
|||
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -slp-vectorizer -dce < %s | FileCheck -check-prefixes=GCN,GFX9,GFX89 %s
|
||||
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -slp-vectorizer -dce < %s | FileCheck -check-prefixes=GCN,VI,GFX89 %s
|
||||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -slp-vectorizer -dce < %s | FileCheck -check-prefixes=GCN,GFX9 %s
|
||||
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -slp-vectorizer -dce < %s | FileCheck -check-prefixes=GCN,VI %s
|
||||
|
||||
; FIXME: Should still like to vectorize the memory operations for VI
|
||||
|
||||
; Simple 3-pair chain with loads and stores
|
||||
; GCN-LABEL: @test1_as_3_3_3_v2f16(
|
||||
; GFX89: load <2 x half>, <2 x half> addrspace(3)*
|
||||
; GFX89: load <2 x half>, <2 x half> addrspace(3)*
|
||||
; GFX89: fmul <2 x half>
|
||||
; GFX89: store <2 x half> %{{.*}}, <2 x half> addrspace(3)* %
|
||||
; GFX89: ret
|
||||
define amdgpu_kernel void @test1_as_3_3_3_v2f16(half addrspace(3)* %a, half addrspace(3)* %b, half addrspace(3)* %c) {
|
||||
; GCN-LABEL: @test1_as_3_3_3_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half addrspace(3)* [[B:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = fmul <2 x half> [[TMP2]], [[TMP4]]
|
||||
; GCN-NEXT: [[TMP6:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP5]], <2 x half> addrspace(3)* [[TMP6]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%i1 = load half, half addrspace(3)* %b, align 2
|
||||
%mul = fmul half %i0, %i1
|
||||
|
|
@ -25,13 +30,17 @@ define amdgpu_kernel void @test1_as_3_3_3_v2f16(half addrspace(3)* %a, half addr
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @test1_as_3_0_0(
|
||||
; GFX89: load <2 x half>, <2 x half> addrspace(3)*
|
||||
; GFX89: load <2 x half>, <2 x half>*
|
||||
; GFX89: fmul <2 x half>
|
||||
; GFX89: store <2 x half> %{{.*}}, <2 x half>* %
|
||||
; GFX89: ret
|
||||
define amdgpu_kernel void @test1_as_3_0_0(half addrspace(3)* %a, half* %b, half* %c) {
|
||||
; GCN-LABEL: @test1_as_3_0_0(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half* [[B:%.*]] to <2 x half>*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half>* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = fmul <2 x half> [[TMP2]], [[TMP4]]
|
||||
; GCN-NEXT: [[TMP6:%.*]] = bitcast half* [[C:%.*]] to <2 x half>*
|
||||
; GCN-NEXT: store <2 x half> [[TMP5]], <2 x half>* [[TMP6]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%i1 = load half, half* %b, align 2
|
||||
%mul = fmul half %i0, %i1
|
||||
|
|
@ -46,13 +55,17 @@ define amdgpu_kernel void @test1_as_3_0_0(half addrspace(3)* %a, half* %b, half*
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @test1_as_0_0_3_v2f16(
|
||||
; GFX89: load <2 x half>, <2 x half>*
|
||||
; GFX89: load <2 x half>, <2 x half>*
|
||||
; GFX89: fmul <2 x half>
|
||||
; GFX89: store <2 x half> %{{.*}}, <2 x half> addrspace(3)* %
|
||||
; GFX89: ret
|
||||
define amdgpu_kernel void @test1_as_0_0_3_v2f16(half* %a, half* %b, half addrspace(3)* %c) {
|
||||
; GCN-LABEL: @test1_as_0_0_3_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half* [[A:%.*]] to <2 x half>*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half>* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half* [[B:%.*]] to <2 x half>*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half>* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = fmul <2 x half> [[TMP2]], [[TMP4]]
|
||||
; GCN-NEXT: [[TMP6:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP5]], <2 x half> addrspace(3)* [[TMP6]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half* %a, align 2
|
||||
%i1 = load half, half* %b, align 2
|
||||
%mul = fmul half %i0, %i1
|
||||
|
|
@ -67,13 +80,19 @@ define amdgpu_kernel void @test1_as_0_0_3_v2f16(half* %a, half* %b, half addrspa
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @test1_fma_v2f16(
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: call <2 x half> @llvm.fma.v2f16(
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @test1_fma_v2f16(half addrspace(3)* %a, half addrspace(3)* %b, half addrspace(3)* %c, half addrspace(3)* %d) {
|
||||
; GCN-LABEL: @test1_fma_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half addrspace(3)* [[B:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP6:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP5]], align 2
|
||||
; GCN-NEXT: [[TMP7:%.*]] = call <2 x half> @llvm.fma.v2f16(<2 x half> [[TMP2]], <2 x half> [[TMP4]], <2 x half> [[TMP6]])
|
||||
; GCN-NEXT: [[TMP8:%.*]] = bitcast half addrspace(3)* [[D:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP7]], <2 x half> addrspace(3)* [[TMP8]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%i1 = load half, half addrspace(3)* %b, align 2
|
||||
%i2 = load half, half addrspace(3)* %c, align 2
|
||||
|
|
@ -91,11 +110,17 @@ define amdgpu_kernel void @test1_fma_v2f16(half addrspace(3)* %a, half addrspace
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @mul_scalar_v2f16(
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: fmul <2 x half>
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @mul_scalar_v2f16(half addrspace(3)* %a, half %scalar, half addrspace(3)* %c) {
|
||||
; GCN-LABEL: @mul_scalar_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = insertelement <2 x half> undef, half [[SCALAR:%.*]], i32 0
|
||||
; GCN-NEXT: [[TMP4:%.*]] = insertelement <2 x half> [[TMP3]], half [[SCALAR]], i32 1
|
||||
; GCN-NEXT: [[TMP5:%.*]] = fmul <2 x half> [[TMP2]], [[TMP4]]
|
||||
; GCN-NEXT: [[TMP6:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP5]], <2 x half> addrspace(3)* [[TMP6]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%mul = fmul half %i0, %scalar
|
||||
%arrayidx3 = getelementptr inbounds half, half addrspace(3)* %a, i64 1
|
||||
|
|
@ -107,11 +132,15 @@ define amdgpu_kernel void @mul_scalar_v2f16(half addrspace(3)* %a, half %scalar,
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @fabs_v2f16
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: call <2 x half> @llvm.fabs.v2f16(
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @fabs_v2f16(half addrspace(3)* %a, half addrspace(3)* %c) {
|
||||
; GCN-LABEL: @fabs_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = call <2 x half> @llvm.fabs.v2f16(<2 x half> [[TMP2]])
|
||||
; GCN-NEXT: [[TMP4:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP3]], <2 x half> addrspace(3)* [[TMP4]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%fabs0 = call half @llvm.fabs.f16(half %i0)
|
||||
%arrayidx3 = getelementptr inbounds half, half addrspace(3)* %a, i64 1
|
||||
|
|
@ -123,12 +152,20 @@ define amdgpu_kernel void @fabs_v2f16(half addrspace(3)* %a, half addrspace(3)*
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @test1_fabs_fma_v2f16(
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: call <2 x half> @llvm.fabs.v2f16(
|
||||
; GFX9: call <2 x half> @llvm.fma.v2f16(
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @test1_fabs_fma_v2f16(half addrspace(3)* %a, half addrspace(3)* %b, half addrspace(3)* %c, half addrspace(3)* %d) {
|
||||
; GCN-LABEL: @test1_fabs_fma_v2f16(
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half addrspace(3)* [[B:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP6:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP5]], align 2
|
||||
; GCN-NEXT: [[TMP7:%.*]] = call <2 x half> @llvm.fabs.v2f16(<2 x half> [[TMP2]])
|
||||
; GCN-NEXT: [[TMP8:%.*]] = call <2 x half> @llvm.fma.v2f16(<2 x half> [[TMP7]], <2 x half> [[TMP4]], <2 x half> [[TMP6]])
|
||||
; GCN-NEXT: [[TMP9:%.*]] = bitcast half addrspace(3)* [[D:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP8]], <2 x half> addrspace(3)* [[TMP9]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%i1 = load half, half addrspace(3)* %b, align 2
|
||||
%i2 = load half, half addrspace(3)* %c, align 2
|
||||
|
|
@ -150,16 +187,23 @@ define amdgpu_kernel void @test1_fabs_fma_v2f16(half addrspace(3)* %a, half addr
|
|||
ret void
|
||||
}
|
||||
|
||||
; FIXME: Should do vector load and extract component for fabs
|
||||
; GCN-LABEL: @test1_fabs_scalar_fma_v2f16(
|
||||
; GFX9: load half
|
||||
; GFX9: call half @llvm.fabs.f16(
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: load half
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: call <2 x half> @llvm.fma.v2f16(
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @test1_fabs_scalar_fma_v2f16(half addrspace(3)* %a, half addrspace(3)* %b, half addrspace(3)* %c, half addrspace(3)* %d) {
|
||||
; GCN-LABEL: @test1_fabs_scalar_fma_v2f16(
|
||||
; GCN-NEXT: [[I1:%.*]] = load half, half addrspace(3)* [[B:%.*]], align 2
|
||||
; GCN-NEXT: [[I1_FABS:%.*]] = call half @llvm.fabs.f16(half [[I1]])
|
||||
; GCN-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GCN-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds half, half addrspace(3)* [[B]], i64 1
|
||||
; GCN-NEXT: [[I4:%.*]] = load half, half addrspace(3)* [[ARRAYIDX4]], align 2
|
||||
; GCN-NEXT: [[TMP3:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: [[TMP4:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP3]], align 2
|
||||
; GCN-NEXT: [[TMP5:%.*]] = insertelement <2 x half> undef, half [[I1_FABS]], i32 0
|
||||
; GCN-NEXT: [[TMP6:%.*]] = insertelement <2 x half> [[TMP5]], half [[I4]], i32 1
|
||||
; GCN-NEXT: [[TMP7:%.*]] = call <2 x half> @llvm.fma.v2f16(<2 x half> [[TMP2]], <2 x half> [[TMP6]], <2 x half> [[TMP4]])
|
||||
; GCN-NEXT: [[TMP8:%.*]] = bitcast half addrspace(3)* [[D:%.*]] to <2 x half> addrspace(3)*
|
||||
; GCN-NEXT: store <2 x half> [[TMP7]], <2 x half> addrspace(3)* [[TMP8]], align 2
|
||||
; GCN-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%i1 = load half, half addrspace(3)* %b, align 2
|
||||
%i2 = load half, half addrspace(3)* %c, align 2
|
||||
|
|
@ -179,11 +223,26 @@ define amdgpu_kernel void @test1_fabs_scalar_fma_v2f16(half addrspace(3)* %a, ha
|
|||
ret void
|
||||
}
|
||||
|
||||
; GCN-LABEL: @canonicalize_v2f16
|
||||
; GFX9: load <2 x half>
|
||||
; GFX9: call <2 x half> @llvm.canonicalize.v2f16(
|
||||
; GFX9: store <2 x half>
|
||||
define amdgpu_kernel void @canonicalize_v2f16(half addrspace(3)* %a, half addrspace(3)* %c) {
|
||||
; GFX9-LABEL: @canonicalize_v2f16(
|
||||
; GFX9-NEXT: [[TMP1:%.*]] = bitcast half addrspace(3)* [[A:%.*]] to <2 x half> addrspace(3)*
|
||||
; GFX9-NEXT: [[TMP2:%.*]] = load <2 x half>, <2 x half> addrspace(3)* [[TMP1]], align 2
|
||||
; GFX9-NEXT: [[TMP3:%.*]] = call <2 x half> @llvm.canonicalize.v2f16(<2 x half> [[TMP2]])
|
||||
; GFX9-NEXT: [[TMP4:%.*]] = bitcast half addrspace(3)* [[C:%.*]] to <2 x half> addrspace(3)*
|
||||
; GFX9-NEXT: store <2 x half> [[TMP3]], <2 x half> addrspace(3)* [[TMP4]], align 2
|
||||
; GFX9-NEXT: ret void
|
||||
;
|
||||
; VI-LABEL: @canonicalize_v2f16(
|
||||
; VI-NEXT: [[I0:%.*]] = load half, half addrspace(3)* [[A:%.*]], align 2
|
||||
; VI-NEXT: [[CANONICALIZE0:%.*]] = call half @llvm.canonicalize.f16(half [[I0]])
|
||||
; VI-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds half, half addrspace(3)* [[A]], i64 1
|
||||
; VI-NEXT: [[I3:%.*]] = load half, half addrspace(3)* [[ARRAYIDX3]], align 2
|
||||
; VI-NEXT: [[CANONICALIZE1:%.*]] = call half @llvm.canonicalize.f16(half [[I3]])
|
||||
; VI-NEXT: store half [[CANONICALIZE0]], half addrspace(3)* [[C:%.*]], align 2
|
||||
; VI-NEXT: [[ARRAYIDX5:%.*]] = getelementptr inbounds half, half addrspace(3)* [[C]], i64 1
|
||||
; VI-NEXT: store half [[CANONICALIZE1]], half addrspace(3)* [[ARRAYIDX5]], align 2
|
||||
; VI-NEXT: ret void
|
||||
;
|
||||
%i0 = load half, half addrspace(3)* %a, align 2
|
||||
%canonicalize0 = call half @llvm.canonicalize.f16(half %i0)
|
||||
%arrayidx3 = getelementptr inbounds half, half addrspace(3)* %a, i64 1
|
||||
|
|
|
|||
Loading…
Reference in New Issue