derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
202 lines
11 KiB
LLVM
202 lines
11 KiB
LLVM
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s -check-prefix=SVE
|
|
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s --check-prefix=SVE2
|
|
|
|
; SRHADD
|
|
|
|
define void @srhadd_i8_sext_i16_fixed(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'srhadd_i8_sext_i16_fixed'
|
|
; SVE: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = sext <16 x i8> %ld1 to <16 x i16>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = sext <16 x i8> %ld2 to <16 x i16>
|
|
;
|
|
; SVE2-LABEL: 'srhadd_i8_sext_i16_fixed'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = sext <16 x i8> %ld1 to <16 x i16>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = sext <16 x i8> %ld2 to <16 x i16>
|
|
;
|
|
%ld1 = load <16 x i8>, ptr %a
|
|
%ld2 = load <16 x i8>, ptr %b
|
|
%ext1 = sext <16 x i8> %ld1 to <16 x i16>
|
|
%ext2 = sext <16 x i8> %ld2 to <16 x i16>
|
|
%add1 = add nuw nsw <16 x i16> %ext1, shufflevector (<16 x i16> insertelement (<16 x i16> poison, i16 1, i64 0), <16 x i16> poison, <16 x i32> zeroinitializer)
|
|
%add2 = add nuw nsw <16 x i16> %add1, %ext2
|
|
%shr = lshr <16 x i16> %add2, shufflevector (<16 x i16> insertelement (<16 x i16> poison, i16 1, i64 0), <16 x i16> poison, <16 x i32> zeroinitializer)
|
|
%trunc = trunc <16 x i16> %shr to <16 x i8>
|
|
store <16 x i8> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @srhadd_i8_sext_i16_scalable(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'srhadd_i8_sext_i16_scalable'
|
|
; SVE: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = sext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
; SVE2-LABEL: 'srhadd_i8_sext_i16_scalable'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = sext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
%ld1 = load <vscale x 16 x i8>, ptr %a
|
|
%ld2 = load <vscale x 16 x i8>, ptr %b
|
|
%ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
%ext2 = sext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
%add1 = add nuw nsw <vscale x 16 x i16> %ext1, splat (i16 1)
|
|
%add2 = add nuw nsw <vscale x 16 x i16> %add1, %ext2
|
|
%shr = lshr <vscale x 16 x i16> %add2, splat (i16 1)
|
|
%trunc = trunc <vscale x 16 x i16> %shr to <vscale x 16 x i8>
|
|
store <vscale x 16 x i8> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @srhadd_i16_sext_i64_scalable(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'srhadd_i16_sext_i64_scalable'
|
|
; SVE: Cost Model: Found an estimated cost of 6 for instruction: %ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i64>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i64>
|
|
;
|
|
; SVE2-LABEL: 'srhadd_i16_sext_i64_scalable'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i64>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i64>
|
|
;
|
|
%ld1 = load <vscale x 8 x i16>, ptr %a
|
|
%ld2 = load <vscale x 8 x i16>, ptr %b
|
|
%ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i64>
|
|
%ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i64>
|
|
%add1 = add nuw nsw <vscale x 8 x i64> %ext1, splat (i64 1)
|
|
%add2 = add nuw nsw <vscale x 8 x i64> %add1, %ext2
|
|
%shr = lshr <vscale x 8 x i64> %add2, splat (i64 1)
|
|
%trunc = trunc <vscale x 8 x i64> %shr to <vscale x 8 x i16>
|
|
store <vscale x 8 x i16> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
; URHADD
|
|
|
|
define void @urhadd_i32_zext_i64_fixed(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'urhadd_i32_zext_i64_fixed'
|
|
; SVE: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = zext <4 x i32> %ld1 to <4 x i64>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = zext <4 x i32> %ld2 to <4 x i64>
|
|
;
|
|
; SVE2-LABEL: 'urhadd_i32_zext_i64_fixed'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = zext <4 x i32> %ld1 to <4 x i64>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = zext <4 x i32> %ld2 to <4 x i64>
|
|
;
|
|
%ld1 = load <4 x i32>, ptr %a
|
|
%ld2 = load <4 x i32>, ptr %b
|
|
%ext1 = zext <4 x i32> %ld1 to <4 x i64>
|
|
%ext2 = zext <4 x i32> %ld2 to <4 x i64>
|
|
%add1 = add nuw nsw <4 x i64> %ext1, shufflevector (<4 x i64> insertelement (<4 x i64> poison, i64 1, i64 0), <4 x i64> poison, <4 x i32> zeroinitializer)
|
|
%add2 = add nuw nsw <4 x i64> %add1, %ext2
|
|
%shr = lshr <4 x i64> %add2, shufflevector (<4 x i64> insertelement (<4 x i64> poison, i64 1, i64 0), <4 x i64> poison, <4 x i32> zeroinitializer)
|
|
%trunc = trunc <4 x i64> %shr to <4 x i32>
|
|
store <4 x i32> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @urhadd_i8_zext_i64(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'urhadd_i8_zext_i64'
|
|
; SVE: Cost Model: Found an estimated cost of 14 for instruction: %ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i64>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i64>
|
|
;
|
|
; SVE2-LABEL: 'urhadd_i8_zext_i64'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i64>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i64>
|
|
;
|
|
%ld1 = load <vscale x 16 x i8>, ptr %a
|
|
%ld2 = load <vscale x 16 x i8>, ptr %b
|
|
%ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i64>
|
|
%ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i64>
|
|
%add1 = add nuw nsw <vscale x 16 x i64> %ext1, splat (i64 1)
|
|
%add2 = add nuw nsw <vscale x 16 x i64> %add1, %ext2
|
|
%shr = lshr <vscale x 16 x i64> %add2, splat (i64 1)
|
|
%trunc = trunc <vscale x 16 x i64> %shr to <vscale x 16 x i8>
|
|
store <vscale x 16 x i8> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @urhadd_i16_zext_i32(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'urhadd_i16_zext_i32'
|
|
; SVE: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = zext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = zext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
;
|
|
; SVE2-LABEL: 'urhadd_i16_zext_i32'
|
|
; SVE2: Cost Model: Found an estimated cost of 0 for instruction: %ext1 = zext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %ext2 = zext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
;
|
|
%ld1 = load <vscale x 8 x i16>, ptr %a
|
|
%ld2 = load <vscale x 8 x i16>, ptr %b
|
|
%ext1 = zext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
%ext2 = zext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
%add1 = add nuw nsw <vscale x 8 x i32> %ext1, splat (i32 1)
|
|
%add2 = add nuw nsw <vscale x 8 x i32> %add1, %ext2
|
|
%shr = lshr <vscale x 8 x i32> %add2, splat (i32 1)
|
|
%trunc = trunc <vscale x 8 x i32> %shr to <vscale x 8 x i16>
|
|
store <vscale x 8 x i16> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
; NEGATIVE TESTS
|
|
|
|
define void @ext_operand_mismatch(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'ext_operand_mismatch'
|
|
; SVE: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
; SVE2-LABEL: 'ext_operand_mismatch'
|
|
; SVE2: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
%ld1 = load <vscale x 16 x i8>, ptr %a
|
|
%ld2 = load <vscale x 16 x i8>, ptr %b
|
|
%ext1 = sext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
%ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
%add1 = add nuw nsw <vscale x 16 x i16> %ext1, splat (i16 1)
|
|
%add2 = add nuw nsw <vscale x 16 x i16> %add1, %ext2
|
|
%shr = lshr <vscale x 16 x i16> %add2, splat (i16 1)
|
|
%trunc = trunc <vscale x 16 x i16> %shr to <vscale x 16 x i8>
|
|
store <vscale x 16 x i8> %trunc, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @add_multiple_uses(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'add_multiple_uses'
|
|
; SVE: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
;
|
|
; SVE2-LABEL: 'add_multiple_uses'
|
|
; SVE2: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
;
|
|
%ld1 = load <vscale x 8 x i16>, ptr %a
|
|
%ld2 = load <vscale x 8 x i16>, ptr %b
|
|
%ext1 = sext <vscale x 8 x i16> %ld1 to <vscale x 8 x i32>
|
|
%ext2 = sext <vscale x 8 x i16> %ld2 to <vscale x 8 x i32>
|
|
%add1 = add nuw nsw <vscale x 8 x i32> %ext1, splat (i32 1)
|
|
%add2 = add nuw nsw <vscale x 8 x i32> %add1, %ext2
|
|
%shr = lshr <vscale x 8 x i32> %add2, splat (i32 1)
|
|
%trunc = trunc <vscale x 8 x i32> %shr to <vscale x 8 x i16>
|
|
%add.res = add nuw nsw <vscale x 8 x i32> %add1, %add2
|
|
%res = trunc <vscale x 8 x i32> %add.res to <vscale x 8 x i16>
|
|
store <vscale x 8 x i16> %res, ptr %a
|
|
ret void
|
|
}
|
|
|
|
define void @shift_multiple_uses(ptr %a, ptr %b, ptr %dst) {
|
|
; SVE-LABEL: 'shift_multiple_uses'
|
|
; SVE: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
; SVE2-LABEL: 'shift_multiple_uses'
|
|
; SVE2: Cost Model: Found an estimated cost of 2 for instruction: %ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
; SVE2-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
;
|
|
%ld1 = load <vscale x 16 x i8>, ptr %a
|
|
%ld2 = load <vscale x 16 x i8>, ptr %b
|
|
%ext1 = zext <vscale x 16 x i8> %ld1 to <vscale x 16 x i16>
|
|
%ext2 = zext <vscale x 16 x i8> %ld2 to <vscale x 16 x i16>
|
|
%add1 = add nuw nsw <vscale x 16 x i16> %ext1, splat (i16 1)
|
|
%add2 = add nuw nsw <vscale x 16 x i16> %add1, %ext2
|
|
%shr = lshr <vscale x 16 x i16> %add2, splat (i16 1)
|
|
%trunc = trunc <vscale x 16 x i16> %shr to <vscale x 16 x i8>
|
|
%add3 = add nuw nsw <vscale x 16 x i16> %shr, %add2
|
|
%res = trunc <vscale x 16 x i16> %add3 to <vscale x 16 x i8>
|
|
store <vscale x 16 x i8> %res, ptr %a
|
|
ret void
|
|
}
|