// // Generated by LLVM NVPTX Back-End // .version 8.2 .target sm_90a .address_size 64 // .globl triton_gelu_kernel_0d1d2de .visible .entry triton_gelu_kernel_0d1d2de( .param .u64 triton_gelu_kernel_0d1d2de_param_0, .param .u64 triton_gelu_kernel_0d1d2de_param_1, .param .u32 triton_gelu_kernel_0d1d2de_param_2 ) .maxntid 128, 1, 1 { .reg .pred %p<5>; .reg .b32 %r<49>; .reg .f32 %f<113>; .reg .b64 %rd<8>; .loc 1 484 0 $L__func_begin0: .loc 1 484 0 ld.param.u64 %rd5, [triton_gelu_kernel_0d1d2de_param_0]; ld.param.u64 %rd6, [triton_gelu_kernel_0d1d2de_param_1]; $L__tmp0: .loc 1 493 41 mov.u32 %r42, %tid.x; shl.b32 %r43, %r42, 2; ld.param.u32 %r44, [triton_gelu_kernel_0d1d2de_param_2]; and.b32 %r45, %r43, 508; .loc 1 489 24 mov.u32 %r1, %ctaid.x; .loc 1 490 24 shl.b32 %r46, %r1, 10; .loc 1 493 28 or.b32 %r47, %r46, %r45; or.b32 %r48, %r47, 512; .loc 1 496 21 setp.lt.s32 %p1, %r47, %r44; setp.lt.s32 %p2, %r48, %r44; .loc 1 499 24 mul.wide.s32 %rd7, %r47, 4; add.s64 %rd1, %rd5, %rd7; add.s64 %rd2, %rd1, 2048; .loc 1 499 16 mov.u32 %r2, 0x0; mov.u32 %r3, 0x0; mov.u32 %r4, 0x0; mov.u32 %r5, 0x0; @%p1 ld.global.v4.b32 { %r2, %r3, %r4, %r5 }, [ %rd1 + 0 ]; mov.b32 %f17, %r2; mov.b32 %f18, %r3; mov.b32 %f19, %r4; mov.b32 %f20, %r5; mov.u32 %r6, 0x0; mov.u32 %r7, 0x0; mov.u32 %r8, 0x0; mov.u32 %r9, 0x0; @%p2 ld.global.v4.b32 { %r6, %r7, %r8, %r9 }, [ %rd2 + 0 ]; mov.b32 %f21, %r6; mov.b32 %f22, %r7; mov.b32 %f23, %r8; mov.b32 %f24, %r9; .loc 1 502 37 mul.f32 %f25, %f17, 0f3D372713; mul.f32 %f26, %f18, 0f3D372713; mul.f32 %f27, %f19, 0f3D372713; mul.f32 %f28, %f20, 0f3D372713; mul.f32 %f29, %f21, 0f3D372713; mul.f32 %f30, %f22, 0f3D372713; mul.f32 %f31, %f23, 0f3D372713; mul.f32 %f32, %f24, 0f3D372713; .loc 1 502 41 mul.f32 %f33, %f25, %f17; mul.f32 %f34, %f26, %f18; mul.f32 %f35, %f27, %f19; mul.f32 %f36, %f28, %f20; mul.f32 %f37, %f29, %f21; mul.f32 %f38, %f30, %f22; mul.f32 %f39, %f31, %f23; mul.f32 %f40, %f32, %f24; .loc 1 502 26 fma.rn.f32 %f41, %f33, %f17, %f17; fma.rn.f32 %f42, %f34, %f18, %f18; fma.rn.f32 %f43, %f35, %f19, %f19; fma.rn.f32 %f44, %f36, %f20, %f20; fma.rn.f32 %f45, %f37, %f21, %f21; fma.rn.f32 %f46, %f38, %f22, %f22; fma.rn.f32 %f47, %f39, %f23, %f23; fma.rn.f32 %f48, %f40, %f24, %f24; .loc 1 502 22 mul.f32 %f49, %f41, 0f3F4C422A; mul.f32 %f50, %f42, 0f3F4C422A; mul.f32 %f51, %f43, 0f3F4C422A; mul.f32 %f52, %f44, 0f3F4C422A; mul.f32 %f53, %f45, 0f3F4C422A; mul.f32 %f54, %f46, 0f3F4C422A; mul.f32 %f55, %f47, 0f3F4C422A; mul.f32 %f56, %f48, 0f3F4C422A; .loc 1 503 21 fma.rn.f32 %f57, %f41, 0f3F4C422A, %f49; fma.rn.f32 %f58, %f42, 0f3F4C422A, %f50; fma.rn.f32 %f59, %f43, 0f3F4C422A, %f51; fma.rn.f32 %f60, %f44, 0f3F4C422A, %f52; fma.rn.f32 %f61, %f45, 0f3F4C422A, %f53; fma.rn.f32 %f62, %f46, 0f3F4C422A, %f54; fma.rn.f32 %f63, %f47, 0f3F4C422A, %f55; fma.rn.f32 %f64, %f48, 0f3F4C422A, %f56; .loc 1 503 17 mul.f32 %f2, %f57, 0f3FB8AA3B; ex2.approx.f32 %f1, %f2; mul.f32 %f4, %f58, 0f3FB8AA3B; ex2.approx.f32 %f3, %f4; mul.f32 %f6, %f59, 0f3FB8AA3B; ex2.approx.f32 %f5, %f6; mul.f32 %f8, %f60, 0f3FB8AA3B; ex2.approx.f32 %f7, %f8; mul.f32 %f10, %f61, 0f3FB8AA3B; ex2.approx.f32 %f9, %f10; mul.f32 %f12, %f62, 0f3FB8AA3B; ex2.approx.f32 %f11, %f12; mul.f32 %f14, %f63, 0f3FB8AA3B; ex2.approx.f32 %f13, %f14; mul.f32 %f16, %f64, 0f3FB8AA3B; ex2.approx.f32 %f15, %f16; .loc 1 504 18 add.f32 %f65, %f1, 0fBF800000; add.f32 %f66, %f3, 0fBF800000; add.f32 %f67, %f5, 0fBF800000; add.f32 %f68, %f7, 0fBF800000; add.f32 %f69, %f9, 0fBF800000; add.f32 %f70, %f11, 0fBF800000; add.f32 %f71, %f13, 0fBF800000; add.f32 %f72, %f15, 0fBF800000; .loc 1 504 30 add.f32 %f73, %f1, 0f3F800000; add.f32 %f74, %f3, 0f3F800000; add.f32 %f75, %f5, 0f3F800000; add.f32 %f76, %f7, 0f3F800000; add.f32 %f77, %f9, 0f3F800000; add.f32 %f78, %f11, 0f3F800000; add.f32 %f79, %f13, 0f3F800000; add.f32 %f80, %f15, 0f3F800000; .loc 1 504 24 mov.b32 %r11, %f65; mov.b32 %r12, %f73; div.full.f32 %r10, %r11, %r12; mov.b32 %f81, %r10; mov.b32 %r14, %f66; mov.b32 %r15, %f74; div.full.f32 %r13, %r14, %r15; mov.b32 %f82, %r13; mov.b32 %r17, %f67; mov.b32 %r18, %f75; div.full.f32 %r16, %r17, %r18; mov.b32 %f83, %r16; mov.b32 %r20, %f68; mov.b32 %r21, %f76; div.full.f32 %r19, %r20, %r21; mov.b32 %f84, %r19; mov.b32 %r23, %f69; mov.b32 %r24, %f77; div.full.f32 %r22, %r23, %r24; mov.b32 %f85, %r22; mov.b32 %r26, %f70; mov.b32 %r27, %f78; div.full.f32 %r25, %r26, %r27; mov.b32 %f86, %r25; mov.b32 %r29, %f71; mov.b32 %r30, %f79; div.full.f32 %r28, %r29, %r30; mov.b32 %f87, %r28; mov.b32 %r32, %f72; mov.b32 %r33, %f80; div.full.f32 %r31, %r32, %r33; mov.b32 %f88, %r31; .loc 1 505 14 mul.f32 %f89, %f17, 0f3F000000; mul.f32 %f90, %f18, 0f3F000000; mul.f32 %f91, %f19, 0f3F000000; mul.f32 %f92, %f20, 0f3F000000; mul.f32 %f93, %f21, 0f3F000000; mul.f32 %f94, %f22, 0f3F000000; mul.f32 %f95, %f23, 0f3F000000; mul.f32 %f96, %f24, 0f3F000000; .loc 1 505 23 add.f32 %f97, %f81, 0f3F800000; add.f32 %f98, %f82, 0f3F800000; add.f32 %f99, %f83, 0f3F800000; add.f32 %f100, %f84, 0f3F800000; add.f32 %f101, %f85, 0f3F800000; add.f32 %f102, %f86, 0f3F800000; add.f32 %f103, %f87, 0f3F800000; add.f32 %f104, %f88, 0f3F800000; .loc 1 505 19 mul.f32 %f105, %f89, %f97; mul.f32 %f106, %f90, %f98; mul.f32 %f107, %f91, %f99; mul.f32 %f108, %f92, %f100; mul.f32 %f109, %f93, %f101; mul.f32 %f110, %f94, %f102; mul.f32 %f111, %f95, %f103; mul.f32 %f112, %f96, %f104; .loc 1 508 21 add.s64 %rd3, %rd6, %rd7; add.s64 %rd4, %rd3, 2048; .loc 1 508 30 mov.b32 %r34, %f105; mov.b32 %r35, %f106; mov.b32 %r36, %f107; mov.b32 %r37, %f108; @%p1 st.global.v4.b32 [ %rd3 + 0 ], { %r34, %r35, %r36, %r37 }; mov.b32 %r38, %f109; mov.b32 %r39, %f110; mov.b32 %r40, %f111; mov.b32 %r41, %f112; @%p2 st.global.v4.b32 [ %rd4 + 0 ], { %r38, %r39, %r40, %r41 }; .loc 1 508 4 ret; $L__tmp1: $L__func_end0: } .file 1 "/home/c-pliang/spring2024-lectures/lecture_06.py" .section .debug_abbrev { .b8 1 .b8 17 .b8 1 .b8 37 .b8 8 .b8 19 .b8 5 .b8 3 .b8 8 .b8 16 .b8 6 .b8 27 .b8 8 .b8 180 .b8 66 .b8 12 .b8 17 .b8 1 .b8 18 .b8 1 .b8 0 .b8 0 .b8 2 .b8 46 .b8 0 .b8 17 .b8 1 .b8 18 .b8 1 .b8 64 .b8 10 .b8 135 .b8 64 .b8 8 .b8 3 .b8 8 .b8 58 .b8 11 .b8 59 .b8 5 .b8 63 .b8 12 .b8 0 .b8 0 .b8 0 } .section .debug_info { .b32 165 .b8 2 .b8 0 .b32 .debug_abbrev .b8 8 .b8 1 .b8 116 .b8 114 .b8 105 .b8 116 .b8 111 .b8 110 .b8 0 .b8 2 .b8 0 .b8 108 .b8 101 .b8 99 .b8 116 .b8 117 .b8 114 .b8 101 .b8 95 .b8 48 .b8 54 .b8 46 .b8 112 .b8 121 .b8 0 .b32 .debug_line .b8 47 .b8 104 .b8 111 .b8 109 .b8 101 .b8 47 .b8 99 .b8 45 .b8 112 .b8 108 .b8 105 .b8 97 .b8 110 .b8 103 .b8 47 .b8 115 .b8 112 .b8 114 .b8 105 .b8 110 .b8 103 .b8 50 .b8 48 .b8 50 .b8 52 .b8 45 .b8 108 .b8 101 .b8 99 .b8 116 .b8 117 .b8 114 .b8 101 .b8 115 .b8 0 .b8 1 .b64 $L__func_begin0 .b64 $L__func_end0 .b8 2 .b64 $L__func_begin0 .b64 $L__func_end0 .b8 1 .b8 156 .b8 116 .b8 114 .b8 105 .b8 116 .b8 111 .b8 110 .b8 95 .b8 103 .b8 101 .b8 108 .b8 117 .b8 95 .b8 107 .b8 101 .b8 114 .b8 110 .b8 101 .b8 108 .b8 95 .b8 48 .b8 100 .b8 49 .b8 100 .b8 50 .b8 100 .b8 101 .b8 0 .b8 116 .b8 114 .b8 105 .b8 116 .b8 111 .b8 110 .b8 95 .b8 103 .b8 101 .b8 108 .b8 117 .b8 95 .b8 107 .b8 101 .b8 114 .b8 110 .b8 101 .b8 108 .b8 95 .b8 48 .b8 100 .b8 49 .b8 100 .b8 50 .b8 100 .b8 101 .b8 0 .b8 1 .b8 228 .b8 1 .b8 1 .b8 0 } .section .debug_pubnames { .b32 $L__pubNames_end0-$L__pubNames_start0 $L__pubNames_start0: .b8 2 .b8 0 .b32 .debug_info .b32 169 .b32 91 .b8 116 .b8 114 .b8 105 .b8 116 .b8 111 .b8 110 .b8 95 .b8 103 .b8 101 .b8 108 .b8 117 .b8 95 .b8 107 .b8 101 .b8 114 .b8 110 .b8 101 .b8 108 .b8 95 .b8 48 .b8 100 .b8 49 .b8 100 .b8 50 .b8 100 .b8 101 .b8 0 .b32 0 $L__pubNames_end0: } .section .debug_pubtypes { .b32 $L__pubTypes_end0-$L__pubTypes_start0 $L__pubTypes_start0: .b8 2 .b8 0 .b32 .debug_info .b32 169 .b32 0 $L__pubTypes_end0: } .section .debug_loc { }