X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=lib%2FTarget%2FPowerPC%2FREADME_ALTIVEC.txt;h=34765de1b2179fffb5ec7ede41a26e9969806fc9;hp=9de4415c3e0c39dd2da3752872f04d0a659a5154;hb=b69d556c370b32dee9f64d8250e51aad33963cc2;hpb=19a815238e55458e95f99b4dad31ed053c9f635c diff --git a/lib/Target/PowerPC/README_ALTIVEC.txt b/lib/Target/PowerPC/README_ALTIVEC.txt index 9de4415c3e0..34765de1b21 100644 --- a/lib/Target/PowerPC/README_ALTIVEC.txt +++ b/lib/Target/PowerPC/README_ALTIVEC.txt @@ -39,16 +39,12 @@ a load/store/lve*x sequence. //===----------------------------------------------------------------------===// -FABS/FNEG can be codegen'd with the appropriate and/xor of -0.0. - -//===----------------------------------------------------------------------===// - For functions that use altivec AND have calls, we are VRSAVE'ing all call clobbered regs. //===----------------------------------------------------------------------===// -Implement passing vectors by value. +Implement passing vectors by value into calls and receiving them as arguments. //===----------------------------------------------------------------------===// @@ -57,21 +53,15 @@ of C1/C2/C3, then a load and vperm of Variable. //===----------------------------------------------------------------------===// -We currently codegen SCALAR_TO_VECTOR as a store of the scalar to a 16-byte -aligned stack slot, followed by a load/vperm. We should probably just store it -to a scalar stack slot, then use lvsl/vperm to load it. If the value is already -in memory, this is a huge win. - -//===----------------------------------------------------------------------===// - -Do not generate the MFCR/RLWINM sequence for predicate compares when the -predicate compare is used immediately by a branch. Just branch on the right -cond code on CR6. +We need a way to teach tblgen that some operands of an intrinsic are required to +be constants. The verifier should enforce this constraint. //===----------------------------------------------------------------------===// -We need a way to teach tblgen that some operands of an intrinsic are required to -be constants. The verifier should enforce this constraint. +We currently codegen SCALAR_TO_VECTOR as a store of the scalar to a 16-byte +aligned stack slot, followed by a load/vperm. We should probably just store it +to a scalar stack slot, then use lvsl/vperm to load it. If the value is already +in memory this is a big win. //===----------------------------------------------------------------------===// @@ -87,10 +77,206 @@ We can do an arbitrary non-constant value by using lvsr/perm/ste. If we want to tie instruction selection into the scheduler, we can do some constant formation with different instructions. For example, we can generate -"vsplti -1" with "vcmpequw R,R" and 1,1,1,1 with "vsubcuw R,R", both of which -use different execution units, thus could help scheduling. +"vsplti -1" with "vcmpequw R,R" and 1,1,1,1 with "vsubcuw R,R", and 0,0,0,0 with +"vsplti 0" or "vxor", each of which use different execution units, thus could +help scheduling. This is probably only reasonable for a post-pass scheduler. //===----------------------------------------------------------------------===// +For this function: + +void test(vector float *A, vector float *B) { + vector float C = (vector float)vec_cmpeq(*A, *B); + if (!vec_any_eq(*A, *B)) + *B = (vector float){0,0,0,0}; + *A = C; +} + +we get the following basic block: + + ... + lvx v2, 0, r4 + lvx v3, 0, r3 + vcmpeqfp v4, v3, v2 + vcmpeqfp. v2, v3, v2 + bne cr6, LBB1_2 ; cond_next + +The vcmpeqfp/vcmpeqfp. instructions currently cannot be merged when the +vcmpeqfp. result is used by a branch. This can be improved. + +//===----------------------------------------------------------------------===// + +The code generated for this is truly aweful: + +vector float test(float a, float b) { + return (vector float){ 0.0, a, 0.0, 0.0}; +} + +LCPI1_0: ; float + .space 4 + .text + .globl _test + .align 4 +_test: + mfspr r2, 256 + oris r3, r2, 4096 + mtspr 256, r3 + lis r3, ha16(LCPI1_0) + addi r4, r1, -32 + stfs f1, -16(r1) + addi r5, r1, -16 + lfs f0, lo16(LCPI1_0)(r3) + stfs f0, -32(r1) + lvx v2, 0, r4 + lvx v3, 0, r5 + vmrghw v3, v3, v2 + vspltw v2, v2, 0 + vmrghw v2, v2, v3 + mtspr 256, r2 + blr + +//===----------------------------------------------------------------------===// + +int foo(vector float *x, vector float *y) { + if (vec_all_eq(*x,*y)) return 3245; + else return 12; +} + +A predicate compare being used in a select_cc should have the same peephole +applied to it as a predicate compare used by a br_cc. There should be no +mfcr here: + +_foo: + mfspr r2, 256 + oris r5, r2, 12288 + mtspr 256, r5 + li r5, 12 + li r6, 3245 + lvx v2, 0, r4 + lvx v3, 0, r3 + vcmpeqfp. v2, v3, v2 + mfcr r3, 2 + rlwinm r3, r3, 25, 31, 31 + cmpwi cr0, r3, 0 + bne cr0, LBB1_2 ; entry +LBB1_1: ; entry + mr r6, r5 +LBB1_2: ; entry + mr r3, r6 + mtspr 256, r2 + blr + +//===----------------------------------------------------------------------===// + +CodeGen/PowerPC/vec_constants.ll has an and operation that should be +codegen'd to andc. The issue is that the 'all ones' build vector is +SelectNodeTo'd a VSPLTISB instruction node before the and/xor is selected +which prevents the vnot pattern from matching. + + +//===----------------------------------------------------------------------===// + +An alternative to the store/store/load approach for illegal insert element +lowering would be: + +1. store element to any ol' slot +2. lvx the slot +3. lvsl 0; splat index; vcmpeq to generate a select mask +4. lvsl slot + x; vperm to rotate result into correct slot +5. vsel result together. + +//===----------------------------------------------------------------------===// + +Should codegen branches on vec_any/vec_all to avoid mfcr. Two examples: + +#include + int f(vector float a, vector float b) + { + int aa = 0; + if (vec_all_ge(a, b)) + aa |= 0x1; + if (vec_any_ge(a,b)) + aa |= 0x2; + return aa; +} + +vector float f(vector float a, vector float b) { + if (vec_any_eq(a, b)) + return a; + else + return b; +} + +//===----------------------------------------------------------------------===// + +We should do a little better with eliminating dead stores. +The stores to the stack are dead since %a and %b are not needed + +; Function Attrs: nounwind +define <16 x i8> @test_vpmsumb() #0 { + entry: + %a = alloca <16 x i8>, align 16 + %b = alloca <16 x i8>, align 16 + store <16 x i8> , <16 x i8>* %a, align 16 + store <16 x i8> , <16 x i8>* %b, align 16 + %0 = load <16 x i8>* %a, align 16 + %1 = load <16 x i8>* %b, align 16 + %2 = call <16 x i8> @llvm.ppc.altivec.crypto.vpmsumb(<16 x i8> %0, <16 x i8> %1) + ret <16 x i8> %2 +} + + +; Function Attrs: nounwind readnone +declare <16 x i8> @llvm.ppc.altivec.crypto.vpmsumb(<16 x i8>, <16 x i8>) #1 + + +Produces the following code with -mtriple=powerpc64-unknown-linux-gnu: +# BB#0: # %entry + addis 3, 2, .LCPI0_0@toc@ha + addis 4, 2, .LCPI0_1@toc@ha + addi 3, 3, .LCPI0_0@toc@l + addi 4, 4, .LCPI0_1@toc@l + lxvw4x 0, 0, 3 + addi 3, 1, -16 + lxvw4x 35, 0, 4 + stxvw4x 0, 0, 3 + ori 2, 2, 0 + lxvw4x 34, 0, 3 + addi 3, 1, -32 + stxvw4x 35, 0, 3 + vpmsumb 2, 2, 3 + blr + .long 0 + .quad 0 + +The two stxvw4x instructions are not needed. +With -mtriple=powerpc64le-unknown-linux-gnu, the associated permutes +are present too. +//===----------------------------------------------------------------------===// + +The following example is found in test/CodeGen/PowerPC/vec_add_sub_doubleword.ll: + +define <2 x i64> @increment_by_val(<2 x i64> %x, i64 %val) nounwind { + %tmpvec = insertelement <2 x i64> , i64 %val, i32 0 + %tmpvec2 = insertelement <2 x i64> %tmpvec, i64 %val, i32 1 + %result = add <2 x i64> %x, %tmpvec2 + ret <2 x i64> %result + +This will generate the following instruction sequence: + std 5, -8(1) + std 5, -16(1) + addi 3, 1, -16 + ori 2, 2, 0 + lxvd2x 35, 0, 3 + vaddudm 2, 2, 3 + blr + +This will almost certainly cause a load-hit-store hazard. +Since val is a value parameter, it should not need to be saved onto +the stack, unless it's being done set up the vector register. Instead, +it would be better to splat teh value into a vector register, and then +remove the (dead) stores to the stack. + +