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
166 lines
4.3 KiB
LLVM
166 lines
4.3 KiB
LLVM
; Test signed high-part i64->i128 multiplications on z14.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z14 -asm-verbose=0 | FileCheck %s
|
|
|
|
declare i64 @foo()
|
|
|
|
; Check sign-extended multiplication in which only the high part is used.
|
|
define i64 @f1(i64 %dummy, i64 %a, i64 %b) {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK-NOT: {{%r[234]}}
|
|
; CHECK: mgrk %r2, %r3, %r4
|
|
; CHECK: br %r14
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check sign-extended multiplication in which only part of the high half
|
|
; is used.
|
|
define i64 @f2(i64 %dummy, i64 %a, i64 %b) {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK-NOT: {{%r[234]}}
|
|
; CHECK: mgrk [[REG:%r[0-9]+]], %r3, %r4
|
|
; CHECK: srlg %r2, [[REG]], 3
|
|
; CHECK: br %r14
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 67
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check sign-extended multiplication in which the result is split into
|
|
; high and low halves.
|
|
define i64 @f3(i64 %dummy, i64 %a, i64 %b) {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK-NOT: {{%r[234]}}
|
|
; CHECK: mgrk %r2, %r3, %r4
|
|
; CHECK: ogr %r2, %r3
|
|
; CHECK: br %r14
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
%low = trunc i128 %mulx to i64
|
|
%or = or i64 %high, %low
|
|
ret i64 %or
|
|
}
|
|
|
|
; Check MG with no displacement.
|
|
define i64 @f4(i64 %dummy, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK-NOT: {{%r[234]}}
|
|
; CHECK: mg %r2, 0(%r4)
|
|
; CHECK: br %r14
|
|
%b = load i64, ptr %src
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check the high end of the aligned MG range.
|
|
define i64 @f5(i64 %dummy, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f5:
|
|
; CHECK: mg %r2, 524280(%r4)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i64, ptr %src, i64 65535
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check the next doubleword up, which requires separate address logic.
|
|
; Other sequences besides this one would be OK.
|
|
define i64 @f6(i64 %dummy, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f6:
|
|
; CHECK: agfi %r4, 524288
|
|
; CHECK: mg %r2, 0(%r4)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i64, ptr %src, i64 65536
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check the high end of the negative aligned MG range.
|
|
define i64 @f7(i64 %dummy, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f7:
|
|
; CHECK: mg %r2, -8(%r4)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i64, ptr %src, i64 -1
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check the low end of the MG range.
|
|
define i64 @f8(i64 %dummy, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f8:
|
|
; CHECK: mg %r2, -524288(%r4)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i64, ptr %src, i64 -65536
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check the next doubleword down, which needs separate address logic.
|
|
; Other sequences besides this one would be OK.
|
|
define i64 @f9(ptr %dest, i64 %a, ptr %src) {
|
|
; CHECK-LABEL: f9:
|
|
; CHECK: agfi %r4, -524296
|
|
; CHECK: mg %r2, 0(%r4)
|
|
; CHECK: br %r14
|
|
%ptr = getelementptr i64, ptr %src, i64 -65537
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|
|
; Check that MG allows an index.
|
|
define i64 @f10(ptr %dest, i64 %a, i64 %src, i64 %index) {
|
|
; CHECK-LABEL: f10:
|
|
; CHECK: mg %r2, 524287(%r5,%r4)
|
|
; CHECK: br %r14
|
|
%add1 = add i64 %src, %index
|
|
%add2 = add i64 %add1, 524287
|
|
%ptr = inttoptr i64 %add2 to ptr
|
|
%b = load i64, ptr %ptr
|
|
%ax = sext i64 %a to i128
|
|
%bx = sext i64 %b to i128
|
|
%mulx = mul i128 %ax, %bx
|
|
%highx = lshr i128 %mulx, 64
|
|
%high = trunc i128 %highx to i64
|
|
ret i64 %high
|
|
}
|
|
|