RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
Code Issues Projects Releases Wiki Activity
42daf3efdc
llvm-mirror/test/CodeGen/AMDGPU/constant-address-space-32bit.ll
Matt Arsenault 006d5f5a93 Reapply "AMDGPU: Add 32-bit constant address space" 
This reverts r324494 and reapplies r324487.

llvm-svn: 324747
2018-02-09 16:57:57 +00:00

289 lines
15 KiB
LLVM
Raw Blame History

; RUN: llc -march=amdgcn -mcpu=tahiti < %s | FileCheck -check-prefixes=GCN,SICI,SI %s
; RUN: llc -march=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefixes=GCN,SICI %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefixes=GCN,VIGFX9 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefixes=GCN,VIGFX9 %s
; GCN-LABEL: {{^}}load_i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; SICI-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x2
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x8
define amdgpu_vs float @load_i32(i32 addrspace(6)* inreg %p0, i32 addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr i32, i32 addrspace(6)* %p1, i64 2
%r0 = load i32, i32 addrspace(6)* %p0
%r1 = load i32, i32 addrspace(6)* %gep1
%r = add i32 %r0, %r1
%r2 = bitcast i32 %r to float
ret float %r2
}
; GCN-LABEL: {{^}}load_v2i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x4
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x10
define amdgpu_vs <2 x float> @load_v2i32(<2 x i32> addrspace(6)* inreg %p0, <2 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <2 x i32>, <2 x i32> addrspace(6)* %p1, i64 2
%r0 = load <2 x i32>, <2 x i32> addrspace(6)* %p0
%r1 = load <2 x i32>, <2 x i32> addrspace(6)* %gep1
%r = add <2 x i32> %r0, %r1
%r2 = bitcast <2 x i32> %r to <2 x float>
ret <2 x float> %r2
}
; GCN-LABEL: {{^}}load_v4i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x8
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x20
define amdgpu_vs <4 x float> @load_v4i32(<4 x i32> addrspace(6)* inreg %p0, <4 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <4 x i32>, <4 x i32> addrspace(6)* %p1, i64 2
%r0 = load <4 x i32>, <4 x i32> addrspace(6)* %p0
%r1 = load <4 x i32>, <4 x i32> addrspace(6)* %gep1
%r = add <4 x i32> %r0, %r1
%r2 = bitcast <4 x i32> %r to <4 x float>
ret <4 x float> %r2
}
; GCN-LABEL: {{^}}load_v8i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x10
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x40
define amdgpu_vs <8 x float> @load_v8i32(<8 x i32> addrspace(6)* inreg %p0, <8 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <8 x i32>, <8 x i32> addrspace(6)* %p1, i64 2
%r0 = load <8 x i32>, <8 x i32> addrspace(6)* %p0
%r1 = load <8 x i32>, <8 x i32> addrspace(6)* %gep1
%r = add <8 x i32> %r0, %r1
%r2 = bitcast <8 x i32> %r to <8 x float>
ret <8 x float> %r2
}
; GCN-LABEL: {{^}}load_v16i32:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x20
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x80
define amdgpu_vs <16 x float> @load_v16i32(<16 x i32> addrspace(6)* inreg %p0, <16 x i32> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <16 x i32>, <16 x i32> addrspace(6)* %p1, i64 2
%r0 = load <16 x i32>, <16 x i32> addrspace(6)* %p0
%r1 = load <16 x i32>, <16 x i32> addrspace(6)* %gep1
%r = add <16 x i32> %r0, %r1
%r2 = bitcast <16 x i32> %r to <16 x float>
ret <16 x float> %r2
}
; GCN-LABEL: {{^}}load_float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; SICI-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x2
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[0:1], 0x0
; VIGFX9-DAG: s_load_dword s{{[0-9]}}, s[2:3], 0x8
define amdgpu_vs float @load_float(float addrspace(6)* inreg %p0, float addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr float, float addrspace(6)* %p1, i64 2
%r0 = load float, float addrspace(6)* %p0
%r1 = load float, float addrspace(6)* %gep1
%r = fadd float %r0, %r1
ret float %r
}
; GCN-LABEL: {{^}}load_v2float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x4
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx2 s[{{.*}}], s[2:3], 0x10
define amdgpu_vs <2 x float> @load_v2float(<2 x float> addrspace(6)* inreg %p0, <2 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <2 x float>, <2 x float> addrspace(6)* %p1, i64 2
%r0 = load <2 x float>, <2 x float> addrspace(6)* %p0
%r1 = load <2 x float>, <2 x float> addrspace(6)* %gep1
%r = fadd <2 x float> %r0, %r1
ret <2 x float> %r
}
; GCN-LABEL: {{^}}load_v4float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x8
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx4 s[{{.*}}], s[2:3], 0x20
define amdgpu_vs <4 x float> @load_v4float(<4 x float> addrspace(6)* inreg %p0, <4 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <4 x float>, <4 x float> addrspace(6)* %p1, i64 2
%r0 = load <4 x float>, <4 x float> addrspace(6)* %p0
%r1 = load <4 x float>, <4 x float> addrspace(6)* %gep1
%r = fadd <4 x float> %r0, %r1
ret <4 x float> %r
}
; GCN-LABEL: {{^}}load_v8float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x10
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx8 s[{{.*}}], s[2:3], 0x40
define amdgpu_vs <8 x float> @load_v8float(<8 x float> addrspace(6)* inreg %p0, <8 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <8 x float>, <8 x float> addrspace(6)* %p1, i64 2
%r0 = load <8 x float>, <8 x float> addrspace(6)* %p0
%r1 = load <8 x float>, <8 x float> addrspace(6)* %gep1
%r = fadd <8 x float> %r0, %r1
ret <8 x float> %r
}
; GCN-LABEL: {{^}}load_v16float:
; GCN-DAG: s_mov_b32 s3, 0
; GCN-DAG: s_mov_b32 s2, s1
; GCN-DAG: s_mov_b32 s1, s3
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; SICI-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x20
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[0:1], 0x0
; VIGFX9-DAG: s_load_dwordx16 s[{{.*}}], s[2:3], 0x80
define amdgpu_vs <16 x float> @load_v16float(<16 x float> addrspace(6)* inreg %p0, <16 x float> addrspace(6)* inreg %p1) #0 {
%gep1 = getelementptr <16 x float>, <16 x float> addrspace(6)* %p1, i64 2
%r0 = load <16 x float>, <16 x float> addrspace(6)* %p0
%r1 = load <16 x float>, <16 x float> addrspace(6)* %gep1
%r = fadd <16 x float> %r0, %r1
ret <16 x float> %r
}
; GCN-LABEL: {{^}}load_i32_hi0:
; GCN: s_mov_b32 s1, 0
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hi0(i32 addrspace(6)* inreg %p) #1 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hi1:
; GCN: s_mov_b32 s1, 1
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hi1(i32 addrspace(6)* inreg %p) #2 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hiffff8000:
; GCN: s_movk_i32 s1, 0x8000
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hiffff8000(i32 addrspace(6)* inreg %p) #3 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_i32_hifffffff0:
; GCN: s_mov_b32 s1, -16
; GCN-NEXT: s_load_dword s0, s[0:1], 0x0
define amdgpu_vs i32 @load_i32_hifffffff0(i32 addrspace(6)* inreg %p) #4 {
%r0 = load i32, i32 addrspace(6)* %p
ret i32 %r0
}
; GCN-LABEL: {{^}}load_sampler
; GCN: v_readfirstlane_b32
; GCN-NEXT: v_readfirstlane_b32
; SI: s_nop
; GCN-NEXT: s_load_dwordx8
; GCN-NEXT: s_load_dwordx4
; GCN: image_sample
define amdgpu_ps <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> @load_sampler([0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), float inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, i32, i32, float, i32) #5 {
main_body:
%22 = call nsz float @llvm.amdgcn.interp.mov(i32 2, i32 0, i32 0, i32 %5) #8
%23 = bitcast float %22 to i32
%24 = shl i32 %23, 1
%25 = getelementptr [0 x <8 x i32>], [0 x <8 x i32>] addrspace(6)* %1, i32 0, i32 %24, !amdgpu.uniform !0
%26 = load <8 x i32>, <8 x i32> addrspace(6)* %25, align 32, !invariant.load !0
%27 = shl i32 %23, 2
%28 = or i32 %27, 3
%29 = bitcast [0 x <8 x i32>] addrspace(6)* %1 to [0 x <4 x i32>] addrspace(6)*
%30 = getelementptr [0 x <4 x i32>], [0 x <4 x i32>] addrspace(6)* %29, i32 0, i32 %28, !amdgpu.uniform !0
%31 = load <4 x i32>, <4 x i32> addrspace(6)* %30, align 16, !invariant.load !0
%32 = call nsz <4 x float> @llvm.amdgcn.image.sample.v4f32.v2f32.v8i32(<2 x float> zeroinitializer, <8 x i32> %26, <4 x i32> %31, i32 15, i1 false, i1 false, i1 false, i1 false, i1 false) #8
%33 = extractelement <4 x float> %32, i32 0
%34 = extractelement <4 x float> %32, i32 1
%35 = extractelement <4 x float> %32, i32 2
%36 = extractelement <4 x float> %32, i32 3
%37 = bitcast float %4 to i32
%38 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> undef, i32 %37, 4
%39 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %38, float %33, 5
%40 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %39, float %34, 6
%41 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %40, float %35, 7
%42 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %41, float %36, 8
%43 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %42, float %20, 19
ret <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %43
}
; GCN-LABEL: {{^}}load_sampler_nouniform
; GCN: v_readfirstlane_b32
; GCN-NEXT: v_readfirstlane_b32
; SI: s_nop
; GCN-NEXT: s_load_dwordx8
; GCN-NEXT: s_load_dwordx4
; GCN: image_sample
define amdgpu_ps <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> @load_sampler_nouniform([0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <4 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), [0 x <8 x i32>] addrspace(6)* inreg noalias dereferenceable(18446744073709551615), float inreg, i32 inreg, <2 x i32>, <2 x i32>, <2 x i32>, <3 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, float, float, float, float, float, i32, i32, float, i32) #5 {
main_body:
%22 = call nsz float @llvm.amdgcn.interp.mov(i32 2, i32 0, i32 0, i32 %5) #8
%23 = bitcast float %22 to i32
%24 = shl i32 %23, 1
%25 = getelementptr [0 x <8 x i32>], [0 x <8 x i32>] addrspace(6)* %1, i32 0, i32 %24
%26 = load <8 x i32>, <8 x i32> addrspace(6)* %25, align 32, !invariant.load !0
%27 = shl i32 %23, 2
%28 = or i32 %27, 3
%29 = bitcast [0 x <8 x i32>] addrspace(6)* %1 to [0 x <4 x i32>] addrspace(6)*
%30 = getelementptr [0 x <4 x i32>], [0 x <4 x i32>] addrspace(6)* %29, i32 0, i32 %28
%31 = load <4 x i32>, <4 x i32> addrspace(6)* %30, align 16, !invariant.load !0
%32 = call nsz <4 x float> @llvm.amdgcn.image.sample.v4f32.v2f32.v8i32(<2 x float> zeroinitializer, <8 x i32> %26, <4 x i32> %31, i32 15, i1 false, i1 false, i1 false, i1 false, i1 false) #8
%33 = extractelement <4 x float> %32, i32 0
%34 = extractelement <4 x float> %32, i32 1
%35 = extractelement <4 x float> %32, i32 2
%36 = extractelement <4 x float> %32, i32 3
%37 = bitcast float %4 to i32
%38 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> undef, i32 %37, 4
%39 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %38, float %33, 5
%40 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %39, float %34, 6
%41 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %40, float %35, 7
%42 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %41, float %36, 8
%43 = insertvalue <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %42, float %20, 19
ret <{ i32, i32, i32, i32, i32, float, float, float, float, float, float, float, float, float, float, float, float, float, float, float }> %43
}
; Function Attrs: nounwind readnone speculatable
declare float @llvm.amdgcn.interp.mov(i32, i32, i32, i32) #6
; Function Attrs: nounwind readonly
declare <4 x float> @llvm.amdgcn.image.sample.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #7
!0 = !{}
attributes #0 = { nounwind }
attributes #1 = { nounwind "amdgpu-32bit-address-high-bits"="0" }
attributes #2 = { nounwind "amdgpu-32bit-address-high-bits"="1" }
attributes #3 = { nounwind "amdgpu-32bit-address-high-bits"="0xffff8000" }
attributes #4 = { nounwind "amdgpu-32bit-address-high-bits"="0xfffffff0" }
attributes #5 = { "InitialPSInputAddr"="45175" }
attributes #6 = { nounwind readnone speculatable }
attributes #7 = { nounwind readonly }
attributes #8 = { nounwind readnone }
Reference in New Issue View Git Blame Copy Permalink