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
93 lines
1.7 KiB
ArmAsm
93 lines
1.7 KiB
ArmAsm
# mach: bfin
|
|
|
|
.include "testutils.inc"
|
|
start
|
|
|
|
// This function computes an integer 32x32 multiply,
|
|
// and returns the upper 32 bits of the result.
|
|
// If the complete 64 bit result is required, one must
|
|
// write the partial results as they are computed.
|
|
// To change this code for a fractional 32x32, one needs
|
|
// to adjust the shifts for magnitude of -15, and use a
|
|
// fractional multiply at the end for the upper word halves
|
|
// (instead of the integer one).
|
|
|
|
loadsym P0, input_a;
|
|
loadsym P1, input_b;
|
|
loadsym P2, output;
|
|
P4 = 10;
|
|
LSETUP ( loop1 , loop1end ) LC0 = P4;
|
|
loop1:
|
|
R0 = [ P0 ++ ];
|
|
R1 = [ P1 ++ ];
|
|
|
|
// begin integer double precision routine
|
|
// 32 x 32 -> 32
|
|
|
|
A1 = R0.H * R1.L (M), A0 = R0.L * R1.L (FU);
|
|
A1 += R1.H * R0.L (M,IS);
|
|
A0 = A0 >>> 16;
|
|
A0 += A1;
|
|
A0 = A0 >>> 16;
|
|
A0 += R0.H * R1.H (IS);
|
|
R7 = A0.w;
|
|
|
|
loop1end:
|
|
[ P2 ++ ] = R7; // store 32 bit output
|
|
|
|
// test results
|
|
loadsym P1, output;
|
|
R0 = [ P1 ++ ]; DBGA ( R0.H , 0xfeae ); DBGA ( R0.L , 0xab6b );
|
|
R0 = [ P1 ++ ]; DBGA ( R0.H , 0xfeae ); DBGA ( R0.L , 0xa627 );
|
|
R0 = [ P1 ++ ]; DBGA ( R0.H , 0xfeae ); DBGA ( R0.L , 0xa0e3 );
|
|
R0 = [ P1 ++ ]; DBGA ( R0.H , 0xfeae ); DBGA ( R0.L , 0x9b9f );
|
|
pass
|
|
|
|
.data
|
|
input_a:
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.dw 0x0000
|
|
.dw 0xfabc
|
|
.align 4;
|
|
input_b:
|
|
.dw 0x1000
|
|
.dw 0x4010
|
|
.dw 0x1000
|
|
.dw 0x4011
|
|
.dw 0x1000
|
|
.dw 0x4012
|
|
.dw 0x1000
|
|
.dw 0x4013
|
|
.dw 0x1000
|
|
.dw 0x4014
|
|
.dw 0x1000
|
|
.dw 0x4015
|
|
.dw 0x1000
|
|
.dw 0x4016
|
|
.dw 0x1000
|
|
.dw 0x4017
|
|
.dw 0x1000
|
|
.dw 0x4018
|
|
.dw 0x1000
|
|
.dw 0x4019
|
|
.align 4;
|
|
output:
|
|
.space (40);
|