[Mesa-dev] [PATCH 2/2] R600/SI: add tests for gather4
Tom Stellard
tom at stellard.net
Mon Jun 16 08:48:25 PDT 2014
On Thu, Jun 12, 2014 at 02:11:11AM +0200, Marek Olšák wrote:
> From: Marek Olšák <marek.olsak at amd.com>
>
LGTM.
> ---
> test/CodeGen/R600/llvm.SI.gather4.ll | 508 +++++++++++++++++++++++++++++++++++
> 1 file changed, 508 insertions(+)
> create mode 100644 test/CodeGen/R600/llvm.SI.gather4.ll
>
> diff --git a/test/CodeGen/R600/llvm.SI.gather4.ll b/test/CodeGen/R600/llvm.SI.gather4.ll
> new file mode 100644
> index 0000000..8402faa
> --- /dev/null
> +++ b/test/CodeGen/R600/llvm.SI.gather4.ll
> @@ -0,0 +1,508 @@
> +;RUN: llc < %s -march=r600 -mcpu=verde -verify-machineinstrs | FileCheck %s
> +
> +;CHECK-LABEL: @gather4_v2
> +;CHECK: IMAGE_GATHER4 {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_v2() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.v2i32(<2 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4
> +;CHECK: IMAGE_GATHER4 {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_cl
> +;CHECK: IMAGE_GATHER4_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_cl() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.cl.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_l
> +;CHECK: IMAGE_GATHER4_L {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_l() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.l.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b
> +;CHECK: IMAGE_GATHER4_B {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b_cl
> +;CHECK: IMAGE_GATHER4_B_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b_cl() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.cl.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b_cl_v8
> +;CHECK: IMAGE_GATHER4_B_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b_cl_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.cl.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_lz_v2
> +;CHECK: IMAGE_GATHER4_LZ {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_lz_v2() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.lz.v2i32(<2 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_lz
> +;CHECK: IMAGE_GATHER4_LZ {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_lz() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.lz.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +
> +
> +;CHECK-LABEL: @gather4_o
> +;CHECK: IMAGE_GATHER4_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_cl_o
> +;CHECK: IMAGE_GATHER4_CL_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_cl_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.cl.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_cl_o_v8
> +;CHECK: IMAGE_GATHER4_CL_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_cl_o_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.cl.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_l_o
> +;CHECK: IMAGE_GATHER4_L_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_l_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.l.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_l_o_v8
> +;CHECK: IMAGE_GATHER4_L_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_l_o_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.l.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b_o
> +;CHECK: IMAGE_GATHER4_B_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b_o_v8
> +;CHECK: IMAGE_GATHER4_B_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b_o_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_b_cl_o
> +;CHECK: IMAGE_GATHER4_B_CL_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_b_cl_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.b.cl.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_lz_o
> +;CHECK: IMAGE_GATHER4_LZ_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_lz_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.lz.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +
> +
> +;CHECK-LABEL: @gather4_c
> +;CHECK: IMAGE_GATHER4_C {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_cl
> +;CHECK: IMAGE_GATHER4_C_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_cl() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.cl.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_cl_v8
> +;CHECK: IMAGE_GATHER4_C_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_cl_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.cl.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_l
> +;CHECK: IMAGE_GATHER4_C_L {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_l() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.l.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_l_v8
> +;CHECK: IMAGE_GATHER4_C_L {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_l_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.l.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_b
> +;CHECK: IMAGE_GATHER4_C_B {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_b() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.b.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_b_v8
> +;CHECK: IMAGE_GATHER4_C_B {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_b_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.b.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_b_cl
> +;CHECK: IMAGE_GATHER4_C_B_CL {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_b_cl() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.b.cl.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_lz
> +;CHECK: IMAGE_GATHER4_C_LZ {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_lz() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.lz.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +
> +
> +;CHECK-LABEL: @gather4_c_o
> +;CHECK: IMAGE_GATHER4_C_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_o_v8
> +;CHECK: IMAGE_GATHER4_C_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_o_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_cl_o
> +;CHECK: IMAGE_GATHER4_C_CL_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_cl_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.cl.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_l_o
> +;CHECK: IMAGE_GATHER4_C_L_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_l_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.l.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_b_o
> +;CHECK: IMAGE_GATHER4_C_B_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_b_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.b.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_b_cl_o
> +;CHECK: IMAGE_GATHER4_C_B_CL_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_b_cl_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.b.cl.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_lz_o
> +;CHECK: IMAGE_GATHER4_C_LZ_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_lz_o() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.lz.o.v4i32(<4 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +;CHECK-LABEL: @gather4_c_lz_o_v8
> +;CHECK: IMAGE_GATHER4_C_LZ_O {{v\[[0-9]+:[0-9]+\]}}, 1, 0, 0, -1, 0, 0, 0, 0, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}
> +define void @gather4_c_lz_o_v8() #0 {
> +main_body:
> + %r = call <4 x float> @llvm.SI.gather4.c.lz.o.v8i32(<8 x i32> undef, <32 x i8> undef, <16 x i8> undef, i32 1, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
> + %r0 = extractelement <4 x float> %r, i32 0
> + %r1 = extractelement <4 x float> %r, i32 1
> + %r2 = extractelement <4 x float> %r, i32 2
> + %r3 = extractelement <4 x float> %r, i32 3
> + call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r2, float %r3)
> + ret void
> +}
> +
> +
> +
> +declare <4 x float> @llvm.SI.gather4.v2i32(<2 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.cl.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.l.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.cl.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.cl.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.lz.v2i32(<2 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.lz.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +
> +declare <4 x float> @llvm.SI.gather4.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.cl.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.cl.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.l.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.l.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.b.cl.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.lz.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +
> +declare <4 x float> @llvm.SI.gather4.c.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.cl.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.cl.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.l.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.l.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.b.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.b.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.b.cl.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.lz.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +
> +declare <4 x float> @llvm.SI.gather4.c.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.cl.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.l.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.b.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.b.cl.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.lz.o.v4i32(<4 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +declare <4 x float> @llvm.SI.gather4.c.lz.o.v8i32(<8 x i32>, <32 x i8>, <16 x i8>, i32, i32, i32, i32, i32, i32, i32, i32) #1
> +
> +declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
> +
> +attributes #0 = { "ShaderType"="0" }
> +attributes #1 = { nounwind readnone }
> --
> 1.9.1
>
> _______________________________________________
> mesa-dev mailing list
> mesa-dev at lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/mesa-dev
More information about the llvm-commits
mailing list